Add some models with audio inputs and outputs

This commit is contained in:
Paul
2024-07-02 17:52:32 +00:00
parent cdb1c377b7
commit 3200881e66
12 changed files with 5291 additions and 8 deletions
+778
View File
@@ -0,0 +1,778 @@
{
"url": "https://replicate.com/cjwbw/seamless_communication",
"owner": "cjwbw",
"name": "seamless_communication",
"description": "SeamlessM4T—Massively Multilingual & Multimodal Machine Translation",
"visibility": "public",
"github_url": "https://github.com/chenxwh/seamless_communication",
"paper_url": "https://dl.fbaipublicfiles.com/seamless/seamless_m4t_paper.pdf",
"license_url": "https://github.com/chenxwh/seamless_communication/blob/main/LICENSE",
"run_count": 0,
"cover_image_url": null,
"default_example": {
"id": "habhkrlbto7c6tm7apuk5amq6u",
"model": "cjwbw/seamless_communication",
"version": "668a4fec05a887143e5fe8d45df25ec4c794dd43169b9a11562309b2d45873b0",
"status": "succeeded",
"input": {
"task_name": "S2ST (Speech to Speech translation)",
"input_audio": "https://replicate.delivery/pbxt/JWSAJpKxUszI0scNYatExIXZX2rJ78UBilGXCTq4Ct9BDwTA/sample_input_2.mp3",
"input_text_language": "None",
"max_input_audio_length": 60,
"target_language_text_only": "Norwegian Nynorsk",
"target_language_with_speech": "French"
},
"output": {
"text_output": "Le modèle M4T sans faille de MetaAI démocratise la communication parlée à travers les barrières linguistiques.",
"audio_output": "https://pbxt.replicate.delivery/HSuWXcQA0PbWIBQ3renLWSxbFBKcsCQojUtAQK6eys5038jRA/out.wav"
},
"logs": null,
"error": null,
"metrics": {
"predict_time": 5.103559,
"total_time": 84.660864
},
"created_at": "2023-09-13T20:29:20.589970Z",
"started_at": "2023-09-13T20:30:40.147275Z",
"completed_at": "2023-09-13T20:30:45.250834Z",
"urls": {
"get": "https://api.replicate.com/v1/predictions/habhkrlbto7c6tm7apuk5amq6u",
"cancel": "https://api.replicate.com/v1/predictions/habhkrlbto7c6tm7apuk5amq6u/cancel"
}
},
"latest_version": {
"id": "668a4fec05a887143e5fe8d45df25ec4c794dd43169b9a11562309b2d45873b0",
"created_at": "2023-09-13T20:28:44.472205+00:00",
"cog_version": "0.8.3",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"properties": {
"task_name": {
"allOf": [
{
"$ref": "#/components/schemas/task_name"
}
],
"default": "S2ST (Speech to Speech translation)",
"x-order": 0,
"description": "Choose a task"
},
"input_text": {
"type": "string",
"title": "Input Text",
"x-order": 2,
"description": "Provide input for tasks with text: T2ST and T2TT."
},
"input_audio": {
"type": "string",
"title": "Input Audio",
"format": "uri",
"x-order": 1,
"description": "Provide input file for tasks with speech input: S2ST, S2TT and ASR."
},
"input_text_language": {
"allOf": [
{
"$ref": "#/components/schemas/input_text_language"
}
],
"default": "None",
"x-order": 3,
"description": "Specify language of the input_text for T2ST and T2TT"
},
"max_input_audio_length": {
"type": "number",
"title": "Max Input Audio Length",
"default": 60,
"x-order": 6,
"description": "Set maximum input audio length."
},
"target_language_text_only": {
"allOf": [
{
"$ref": "#/components/schemas/target_language_text_only"
}
],
"default": "Norwegian Nynorsk",
"x-order": 5,
"description": "Set target language for tasks with text output only: S2TT, T2TT and ASR."
},
"target_language_with_speech": {
"allOf": [
{
"$ref": "#/components/schemas/target_language_with_speech"
}
],
"default": "French",
"x-order": 4,
"description": "Set target language for tasks with speech output: S2ST or T2ST. Less languages are available for speech compared to text output."
}
}
},
"Output": {
"$ref": "#/components/schemas/ModelOutput",
"title": "Output"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"task_name": {
"enum": [
"S2ST (Speech to Speech translation)",
"S2TT (Speech to Text translation)",
"T2ST (Text to Speech translation)",
"T2TT (Text to Text translation)",
"ASR (Automatic Speech Recognition)"
],
"type": "string",
"title": "task_name",
"description": "An enumeration."
},
"ModelOutput": {
"type": "object",
"title": "ModelOutput",
"required": [
"text_output"
],
"properties": {
"text_output": {
"type": "string",
"title": "Text Output"
},
"audio_output": {
"type": "string",
"title": "Audio Output",
"format": "uri"
}
}
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"completed",
"start",
"logs",
"output"
],
"uniqueItems": true
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
},
"input_text_language": {
"enum": [
"None",
"Afrikaans",
"Amharic",
"Armenian",
"Assamese",
"Basque",
"Belarusian",
"Bengali",
"Bosnian",
"Bulgarian",
"Burmese",
"Cantonese",
"Catalan",
"Cebuano",
"Central Kurdish",
"Croatian",
"Czech",
"Danish",
"Dutch",
"Egyptian Arabic",
"English",
"Estonian",
"Finnish",
"French",
"Galician",
"Ganda",
"Georgian",
"German",
"Greek",
"Gujarati",
"Halh Mongolian",
"Hebrew",
"Hindi",
"Hungarian",
"Icelandic",
"Igbo",
"Indonesian",
"Irish",
"Italian",
"Japanese",
"Javanese",
"Kannada",
"Kazakh",
"Khmer",
"Korean",
"Kyrgyz",
"Lao",
"Lithuanian",
"Luo",
"Macedonian",
"Maithili",
"Malayalam",
"Maltese",
"Mandarin Chinese",
"Marathi",
"Meitei",
"Modern Standard Arabic",
"Moroccan Arabic",
"Nepali",
"North Azerbaijani",
"Northern Uzbek",
"Norwegian Bokmål",
"Norwegian Nynorsk",
"Nyanja",
"Odia",
"Polish",
"Portuguese",
"Punjabi",
"Romanian",
"Russian",
"Serbian",
"Shona",
"Sindhi",
"Slovak",
"Slovenian",
"Somali",
"Southern Pashto",
"Spanish",
"Standard Latvian",
"Standard Malay",
"Swahili",
"Swedish",
"Tagalog",
"Tajik",
"Tamil",
"Telugu",
"Thai",
"Turkish",
"Ukrainian",
"Urdu",
"Vietnamese",
"Welsh",
"West Central Oromo",
"Western Persian",
"Yoruba",
"Zulu"
],
"type": "string",
"title": "input_text_language",
"description": "An enumeration."
},
"target_language_text_only": {
"enum": [
"Afrikaans",
"Amharic",
"Armenian",
"Assamese",
"Basque",
"Belarusian",
"Bengali",
"Bosnian",
"Bulgarian",
"Burmese",
"Cantonese",
"Catalan",
"Cebuano",
"Central Kurdish",
"Croatian",
"Czech",
"Danish",
"Dutch",
"Egyptian Arabic",
"English",
"Estonian",
"Finnish",
"French",
"Galician",
"Ganda",
"Georgian",
"German",
"Greek",
"Gujarati",
"Halh Mongolian",
"Hebrew",
"Hindi",
"Hungarian",
"Icelandic",
"Igbo",
"Indonesian",
"Irish",
"Italian",
"Japanese",
"Javanese",
"Kannada",
"Kazakh",
"Khmer",
"Korean",
"Kyrgyz",
"Lao",
"Lithuanian",
"Luo",
"Macedonian",
"Maithili",
"Malayalam",
"Maltese",
"Mandarin Chinese",
"Marathi",
"Meitei",
"Modern Standard Arabic",
"Moroccan Arabic",
"Nepali",
"North Azerbaijani",
"Northern Uzbek",
"Norwegian Bokmål",
"Norwegian Nynorsk",
"Nyanja",
"Odia",
"Polish",
"Portuguese",
"Punjabi",
"Romanian",
"Russian",
"Serbian",
"Shona",
"Sindhi",
"Slovak",
"Slovenian",
"Somali",
"Southern Pashto",
"Spanish",
"Standard Latvian",
"Standard Malay",
"Swahili",
"Swedish",
"Tagalog",
"Tajik",
"Tamil",
"Telugu",
"Thai",
"Turkish",
"Ukrainian",
"Urdu",
"Vietnamese",
"Welsh",
"West Central Oromo",
"Western Persian",
"Yoruba",
"Zulu"
],
"type": "string",
"title": "target_language_text_only",
"description": "An enumeration."
},
"target_language_with_speech": {
"enum": [
"Bengali",
"Catalan",
"Czech",
"Danish",
"Dutch",
"English",
"Estonian",
"Finnish",
"French",
"German",
"Hindi",
"Indonesian",
"Italian",
"Japanese",
"Korean",
"Maltese",
"Mandarin Chinese",
"Modern Standard Arabic",
"Northern Uzbek",
"Polish",
"Portuguese",
"Romanian",
"Russian",
"Slovak",
"Spanish",
"Swahili",
"Swedish",
"Tagalog",
"Telugu",
"Thai",
"Turkish",
"Ukrainian",
"Urdu",
"Vietnamese",
"Welsh",
"Western Persian"
],
"type": "string",
"title": "target_language_with_speech",
"description": "An enumeration."
}
}
}
}
}
}
+47 -6
View File
@@ -34,9 +34,9 @@
}
},
"latest_version": {
"id": "a75c919339f65bf00afa96511af653fdbd0ec3cb0f5e6f4350809445eee0e14f",
"created_at": "2024-06-11T18:23:49.034977+00:00",
"cog_version": "v0.9.5+dev",
"id": "69196a237cdc310988a4b12ad64f4b36d10189428c19a18526af708546e1856f",
"created_at": "2024-07-02T06:00:03.657728+00:00",
"cog_version": "v0.10.0-alpha13+dev",
"openapi_schema": {
"info": {
"title": "Cog",
@@ -61,6 +61,24 @@
"operationId": "root__get"
}
},
"/ready": {
"get": {
"summary": "Ready",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Ready Ready Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "ready_ready_get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
@@ -269,17 +287,40 @@
"x-order": 0,
"description": "Image input"
},
"top_k": {
"type": "integer",
"title": "Top K",
"default": 1,
"maximum": 1000,
"minimum": 1,
"x-order": 3,
"description": "Top-K sampling"
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 1,
"description": "Propmt"
"description": "Prompt"
},
"max_length": {
"type": "integer",
"title": "Max Length",
"default": 512,
"maximum": 8192,
"minimum": 1,
"x-order": 2,
"description": "Maximum number of tokens to generate."
}
}
},
"Output": {
"type": "string",
"title": "Output"
"type": "array",
"items": {
"type": "string"
},
"title": "Output",
"x-cog-array-type": "iterator",
"x-cog-array-display": "concatenate"
},
"Status": {
"enum": [
+475
View File
@@ -0,0 +1,475 @@
{
"url": "https://replicate.com/declare-lab/tango",
"owner": "declare-lab",
"name": "tango",
"description": "Tango 2: Use text prompts to make sound effects",
"visibility": "public",
"github_url": "https://github.com/declare-lab/tango",
"paper_url": "https://arxiv.org/pdf/2304.13731.pdf",
"license_url": "https://github.com/declare-lab/tango/blob/master/LICENSE.md",
"run_count": 0,
"cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/3e074eeb-6f95-4c4c-b7d8-38f5b9c3a2fd/tango2.png",
"default_example": {
"id": "4gahgg8fa1rgm0cf6sg80rcgn4",
"model": "declare-lab/tango",
"version": "740e4f5e59bd3b871c9e5b4efbff7ded516d40aa6abf4e95fd5e8dd149b7bc3f",
"status": "succeeded",
"input": {
"model": "tango2",
"steps": 100,
"prompt": "Quiet speech and then and airplane flying away",
"guidance": 3
},
"output": "https://replicate.delivery/pbxt/RqTLAYe5ZM0DEaHQlDwvA9PGLud8TeEwrGkG3fAWY5e62eAWC/output.wav",
"logs": null,
"error": null,
"metrics": {
"predict_time": 12.386586,
"total_time": 184.047861
},
"created_at": "2024-05-01T22:56:56.144000Z",
"started_at": "2024-05-01T22:59:47.805275Z",
"completed_at": "2024-05-01T23:00:00.191861Z",
"urls": {
"get": "https://api.replicate.com/v1/predictions/4gahgg8fa1rgm0cf6sg80rcgn4",
"cancel": "https://api.replicate.com/v1/predictions/4gahgg8fa1rgm0cf6sg80rcgn4/cancel"
}
},
"latest_version": {
"id": "740e4f5e59bd3b871c9e5b4efbff7ded516d40aa6abf4e95fd5e8dd149b7bc3f",
"created_at": "2024-05-01T22:29:30.165543+00:00",
"cog_version": "v0.9.6+dev",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"properties": {
"model": {
"allOf": [
{
"$ref": "#/components/schemas/model"
}
],
"default": "tango2",
"x-order": 1,
"description": "choose a model"
},
"steps": {
"type": "integer",
"title": "Steps",
"default": 100,
"x-order": 2,
"description": "inference steps"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "Quiet speech and then and airplane flying away",
"x-order": 0,
"description": "Input prompt"
},
"guidance": {
"type": "number",
"title": "Guidance",
"default": 3,
"x-order": 3,
"description": "guidance scale"
}
}
},
"model": {
"enum": [
"tango2",
"tango2-full"
],
"type": "string",
"title": "model",
"description": "An enumeration."
},
"Output": {
"type": "string",
"title": "Output",
"format": "uri"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"start",
"output",
"logs",
"completed"
]
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
}
}
}
}
}
}
+565
View File
@@ -0,0 +1,565 @@
{
"url": "https://replicate.com/lucataco/magnet",
"owner": "lucataco",
"name": "magnet",
"description": "MAGNeT: Masked Audio Generation using a Single Non-Autoregressive Transformer",
"visibility": "public",
"github_url": "https://github.com/lucataco/audiocraft",
"paper_url": "https://arxiv.org/abs/2401.04577",
"license_url": "https://github.com/facebookresearch/audiocraft?tab=MIT-1-ov-file#readme",
"run_count": 0,
"cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/b958c60f-aa4a-44ac-b251-34317cd96245/magnet.jpeg",
"default_example": {
"id": "6usmrb3bog2on4b52tcnpt74oa",
"model": "lucataco/magnet",
"version": "e8e2ecd4a1dabb58924aa8300b668290cafae166dd36baf65dad9875877de50e",
"status": "succeeded",
"input": {
"model": "facebook/magnet-small-10secs",
"top_p": 0.9,
"prompt": "80s electronic track with melodic synthesizers, catchy beat and groovy bass",
"max_cfg": 10,
"min_cfg": 1,
"span_score": "prod-stride1",
"variations": 3,
"temperature": 3,
"decoding_steps_stage_1": 20,
"decoding_steps_stage_2": 10,
"decoding_steps_stage_3": 10,
"decoding_steps_stage_4": 10
},
"output": [
"https://replicate.delivery/pbxt/A09884lLfO3qWidseZLbU90KjWL3eteHOcSafheMaucmacXjE/0.wav",
"https://replicate.delivery/pbxt/dG0LoAeZINxcf0xueWgwgNHyF2tQv3Lvo7S7HfEew2JbNurRC/1.wav",
"https://replicate.delivery/pbxt/K55hoe139wzvBqXV4pkfDMfqbqRMaYVnJ6O8M1efLbteacXjE/2.wav"
],
"logs": "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:30: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\nwarnings.warn(\"torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.\")\nspiece.model: 0%| | 0.00/792k [00:00<?, ?B/s]\nspiece.model: 100%|██████████| 792k/792k [00:00<00:00, 31.9MB/s]\ntokenizer.json: 0%| | 0.00/1.39M [00:00<?, ?B/s]\ntokenizer.json: 100%|██████████| 1.39M/1.39M [00:00<00:00, 24.7MB/s]\nconfig.json: 0%| | 0.00/1.21k [00:00<?, ?B/s]\nconfig.json: 100%|██████████| 1.21k/1.21k [00:00<00:00, 10.4MB/s]\nmodel.safetensors: 0%| | 0.00/892M [00:00<?, ?B/s]\nmodel.safetensors: 4%|▎ | 31.5M/892M [00:00<00:05, 171MB/s]\nmodel.safetensors: 7%|▋ | 62.9M/892M [00:00<00:04, 193MB/s]\nmodel.safetensors: 11%|█ | 94.4M/892M [00:00<00:03, 208MB/s]\nmodel.safetensors: 14%|█▍ | 126M/892M [00:00<00:03, 231MB/s] \nmodel.safetensors: 18%|█▊ | 157M/892M [00:00<00:03, 213MB/s]\nmodel.safetensors: 22%|██▏ | 199M/892M [00:00<00:03, 227MB/s]\nmodel.safetensors: 26%|██▌ | 231M/892M [00:01<00:02, 232MB/s]\nmodel.safetensors: 29%|██▉ | 262M/892M [00:01<00:02, 234MB/s]\nmodel.safetensors: 33%|███▎ | 294M/892M [00:01<00:02, 235MB/s]\nmodel.safetensors: 36%|███▋ | 325M/892M [00:01<00:02, 239MB/s]\nmodel.safetensors: 40%|███▉ | 357M/892M [00:01<00:02, 233MB/s]\nmodel.safetensors: 44%|████▎ | 388M/892M [00:01<00:02, 233MB/s]\nmodel.safetensors: 47%|████▋ | 419M/892M [00:01<00:02, 235MB/s]\nmodel.safetensors: 51%|█████ | 451M/892M [00:01<00:01, 236MB/s]\nmodel.safetensors: 54%|█████▍ | 482M/892M [00:02<00:01, 227MB/s]\nmodel.safetensors: 58%|█████▊ | 514M/892M [00:02<00:01, 229MB/s]\nmodel.safetensors: 61%|██████ | 545M/892M [00:02<00:01, 228MB/s]\nmodel.safetensors: 65%|██████▍ | 577M/892M [00:02<00:01, 230MB/s]\nmodel.safetensors: 68%|██████▊ | 608M/892M [00:02<00:01, 238MB/s]\nmodel.safetensors: 72%|███████▏ | 640M/892M [00:02<00:01, 246MB/s]\nmodel.safetensors: 75%|███████▌ | 671M/892M [00:02<00:00, 245MB/s]\nmodel.safetensors: 79%|███████▉ | 703M/892M [00:03<00:00, 244MB/s]\nmodel.safetensors: 82%|████████▏ | 734M/892M [00:03<00:00, 242MB/s]\nmodel.safetensors: 86%|████████▌ | 765M/892M [00:03<00:00, 175MB/s]\nmodel.safetensors: 88%|████████▊ | 786M/892M [00:03<00:00, 155MB/s]\nmodel.safetensors: 92%|█████████▏| 818M/892M [00:03<00:00, 175MB/s]\nmodel.safetensors: 95%|█████████▌| 849M/892M [00:03<00:00, 190MB/s]\nmodel.safetensors: 99%|█████████▉| 881M/892M [00:04<00:00, 200MB/s]\nmodel.safetensors: 100%|██████████| 892M/892M [00:04<00:00, 217MB/s]",
"error": null,
"metrics": {
"predict_time": 14.638626,
"total_time": 110.299311
},
"created_at": "2024-01-17T19:26:53.835883Z",
"started_at": "2024-01-17T19:28:29.496568Z",
"completed_at": "2024-01-17T19:28:44.135194Z",
"urls": {
"get": "https://api.replicate.com/v1/predictions/6usmrb3bog2on4b52tcnpt74oa",
"cancel": "https://api.replicate.com/v1/predictions/6usmrb3bog2on4b52tcnpt74oa/cancel"
}
},
"latest_version": {
"id": "e8e2ecd4a1dabb58924aa8300b668290cafae166dd36baf65dad9875877de50e",
"created_at": "2024-01-17T19:21:50.415392+00:00",
"cog_version": "0.8.6",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"properties": {
"model": {
"allOf": [
{
"$ref": "#/components/schemas/model"
}
],
"default": "facebook/magnet-small-10secs",
"x-order": 1,
"description": "Model to use"
},
"top_p": {
"type": "number",
"title": "Top P",
"default": 0.9,
"maximum": 1,
"minimum": 0,
"x-order": 5,
"description": "Top p for sampling"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "80s electronic track with melodic synthesizers, catchy beat and groovy bass",
"x-order": 0,
"description": "Input Text"
},
"max_cfg": {
"type": "number",
"title": "Max Cfg",
"default": 10,
"x-order": 6,
"description": "Max CFG coefficient"
},
"min_cfg": {
"type": "number",
"title": "Min Cfg",
"default": 1,
"x-order": 7,
"description": "Min CFG coefficient"
},
"span_score": {
"allOf": [
{
"$ref": "#/components/schemas/span_score"
}
],
"default": "prod-stride1",
"x-order": 3
},
"variations": {
"type": "integer",
"title": "Variations",
"default": 3,
"maximum": 4,
"minimum": 1,
"x-order": 2,
"description": "Number of variations to generate"
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 3,
"x-order": 4,
"description": "Temperature for sampling"
},
"decoding_steps_stage_1": {
"type": "integer",
"title": "Decoding Steps Stage 1",
"default": 20,
"x-order": 8,
"description": "Number of decoding steps for stage 1"
},
"decoding_steps_stage_2": {
"type": "integer",
"title": "Decoding Steps Stage 2",
"default": 10,
"x-order": 9,
"description": "Number of decoding steps for stage 2"
},
"decoding_steps_stage_3": {
"type": "integer",
"title": "Decoding Steps Stage 3",
"default": 10,
"x-order": 10,
"description": "Number of decoding steps for stage 3"
},
"decoding_steps_stage_4": {
"type": "integer",
"title": "Decoding Steps Stage 4",
"default": 10,
"x-order": 11,
"description": "Number of decoding steps for stage 4"
}
}
},
"model": {
"enum": [
"facebook/magnet-small-10secs",
"facebook/magnet-medium-10secs",
"facebook/magnet-small-30secs",
"facebook/magnet-medium-30secs",
"facebook/audio-magnet-small",
"facebook/audio-magnet-medium"
],
"type": "string",
"title": "model",
"description": "An enumeration."
},
"Output": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"title": "Output"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"span_score": {
"enum": [
"max-nonoverlap",
"prod-stride1"
],
"type": "string",
"title": "span_score",
"description": "An enumeration."
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"start",
"output",
"logs",
"completed"
]
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
}
}
}
}
}
}
+492
View File
@@ -0,0 +1,492 @@
{
"url": "https://replicate.com/lucataco/xtts-v2",
"owner": "lucataco",
"name": "xtts-v2",
"description": "Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning",
"visibility": "public",
"github_url": "https://github.com/lucataco/cog-xtts-v2",
"paper_url": "https://huggingface.co/coqui/XTTS-v2",
"license_url": "https://coqui.ai/cpml",
"run_count": 0,
"cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/760b1398-2ab5-4e9b-959e-f3fed025c82f/xtts.png",
"default_example": {
"id": "adinmbzbslyshwze5s6qmpzmzu",
"model": "lucataco/xtts-v2",
"version": "49ff6cfa14bd4e7f80f62e2279f82f23dfc2e7970f825f8db5599f8a6213c009",
"status": "succeeded",
"input": {
"text": "Hi there, I'm your new voice clone. Try your best to upload quality audio",
"speaker": "https://replicate.delivery/pbxt/Jt79w0xsT64R1JsiJ0LQRL8UcWspg5J4RFrU6YwEKpOT1ukS/male.wav",
"language": "en",
"cleanup_voice": false
},
"output": "https://replicate.delivery/pbxt/eyESqfNPahnLY0gaohu50zm3nL6d5ZLxKdWMuqSPRqbihfxjA/output.wav",
"logs": "ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nGuessed Channel Layout for Input Stream #0.0 : mono\nInput #0, wav, from '/tmp/tmphmw6jd84male.wav':\nMetadata:\nencoder : Lavf58.29.100\nDuration: 00:00:08.64, bitrate: 705 kb/s\nStream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, mono, s16, 705 kb/s\nStream mapping:\nStream #0:0 -> #0:0 (pcm_s16le (native) -> pcm_s16le (native))\nPress [q] to stop, [?] for help\nOutput #0, wav, to '/tmp/speaker.wav':\nMetadata:\nISFT : Lavf58.76.100\nStream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, mono, s16, 705 kb/s\nMetadata:\nencoder : Lavc58.134.100 pcm_s16le\nsize= 4kB time=00:00:00.00 bitrate=N/A speed=N/A\nsize= 744kB time=00:00:08.63 bitrate= 705.9kbits/s speed=1.75e+03x\nvideo:0kB audio:744kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.010236%\n> Text splitted to sentences.\n[\"Hi there, I'm your new voice clone.\", 'Try your best to upload quality audio']\n> Processing time: 3.3411097526550293\n> Real-time factor: 0.613438166517148",
"error": null,
"metrics": {
"predict_time": 4.303438,
"total_time": 4.319136
},
"created_at": "2023-11-16T16:42:06.735772Z",
"started_at": "2023-11-16T16:42:06.751470Z",
"completed_at": "2023-11-16T16:42:11.054908Z",
"urls": {
"get": "https://api.replicate.com/v1/predictions/adinmbzbslyshwze5s6qmpzmzu",
"cancel": "https://api.replicate.com/v1/predictions/adinmbzbslyshwze5s6qmpzmzu/cancel"
}
},
"latest_version": {
"id": "684bc3855b37866c0c65add2ff39c78f3dea3f4ff103a436465326e0f438d55e",
"created_at": "2023-11-28T15:39:16.308105+00:00",
"cog_version": "0.8.6",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"required": [
"speaker"
],
"properties": {
"text": {
"type": "string",
"title": "Text",
"default": "Hi there, I'm your new voice clone. Try your best to upload quality audio",
"x-order": 0,
"description": "Text to synthesize"
},
"speaker": {
"type": "string",
"title": "Speaker",
"format": "uri",
"x-order": 1,
"description": "Original speaker audio (wav, mp3, m4a, ogg, or flv)"
},
"language": {
"allOf": [
{
"$ref": "#/components/schemas/language"
}
],
"default": "en",
"x-order": 2,
"description": "Output language for the synthesised speech"
},
"cleanup_voice": {
"type": "boolean",
"title": "Cleanup Voice",
"default": false,
"x-order": 3,
"description": "Whether to apply denoising to the speaker audio (microphone recordings)"
}
}
},
"Output": {
"type": "string",
"title": "Output",
"format": "uri"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"language": {
"enum": [
"en",
"es",
"fr",
"de",
"it",
"pt",
"pl",
"tr",
"ru",
"nl",
"cs",
"ar",
"zh",
"hu",
"ko",
"hi"
],
"type": "string",
"title": "language",
"description": "An enumeration."
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"start",
"output",
"logs",
"completed"
]
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
}
}
}
}
}
}
File diff suppressed because one or more lines are too long
+469
View File
@@ -0,0 +1,469 @@
{
"url": "https://replicate.com/nateraw/audio-super-resolution",
"owner": "nateraw",
"name": "audio-super-resolution",
"description": "AudioSR: Versatile Audio Super-resolution at Scale",
"visibility": "public",
"github_url": "https://github.com/haoheliu/versatile_audio_super_resolution",
"paper_url": "https://arxiv.org/abs/2309.07314",
"license_url": "https://huggingface.co/haoheliu/wellsolve_audio_super_resolution_48k/blob/main/README.md",
"run_count": 0,
"cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/6bc4e480-6695-451b-940d-48a3b83a1356/replicate-prediction-jvi5xvlbg4v4.png",
"default_example": {
"id": "qqynzilbxm2t5h6eaywx2p7g54",
"model": "nateraw/audio-super-resolution",
"version": "9c3d3e39fb0cb6aea677264881d8073f835336137b39fdea4e94093319379535",
"status": "succeeded",
"input": {
"seed": 42,
"ddim_steps": 50,
"input_file": "https://replicate.delivery/pbxt/JYv70XQsiZBbSmknfMhGoEb4QYbuyJ9hJkfgjyzCvh4TzPmT/music.wav",
"guidance_scale": 3.5
},
"output": "https://pbxt.replicate.delivery/73xEQwFed8UXSCQpBJuLYgg8ym0vjp2nSidaqWKwcxhUvHzIA/out.wav",
"logs": "\u001b[93m Warning: audio is longer than 10.24 seconds, may degrade the model performance. It's recommand to truncate your audio to 5.12 seconds before input to AudioSR to get the best performance.\u001b[00m\n/src/audiosr/utils.py:109: FutureWarning: Pass sr=48000, n_fft=2048, n_mels=256, fmin=20, fmax=24000 as keyword args. From version 0.10 passing these as positional arguments will result in an error\nmel = librosa_mel_fn(sampling_rate, filter_length, n_mel, mel_fmin, mel_fmax)\nRunning DDIM Sampling with 50 timesteps\nDDIM Sampler: 0%| | 0/50 [00:00<?, ?it/s]\nDDIM Sampler: 2%|▏ | 1/50 [00:06<05:20, 6.54s/it]\nDDIM Sampler: 4%|▍ | 2/50 [00:06<02:14, 2.80s/it]\nDDIM Sampler: 6%|▌ | 3/50 [00:06<01:15, 1.60s/it]\nDDIM Sampler: 8%|▊ | 4/50 [00:07<00:47, 1.04s/it]\nDDIM Sampler: 10%|█ | 5/50 [00:07<00:32, 1.37it/s]\nDDIM Sampler: 12%|█▏ | 6/50 [00:07<00:23, 1.84it/s]\nDDIM Sampler: 14%|█▍ | 7/50 [00:07<00:18, 2.36it/s]\nDDIM Sampler: 16%|█▌ | 8/50 [00:07<00:14, 2.89it/s]\nDDIM Sampler: 18%|█▊ | 9/50 [00:07<00:12, 3.40it/s]\nDDIM Sampler: 20%|██ | 10/50 [00:08<00:10, 3.86it/s]\nDDIM Sampler: 22%|██▏ | 11/50 [00:08<00:09, 4.26it/s]\nDDIM Sampler: 24%|██▍ | 12/50 [00:08<00:08, 4.59it/s]\nDDIM Sampler: 26%|██▌ | 13/50 [00:08<00:07, 4.85it/s]\nDDIM Sampler: 28%|██▊ | 14/50 [00:08<00:07, 5.04it/s]\nDDIM Sampler: 30%|███ | 15/50 [00:09<00:06, 5.19it/s]\nDDIM Sampler: 32%|███▏ | 16/50 [00:09<00:06, 5.29it/s]\nDDIM Sampler: 34%|███▍ | 17/50 [00:09<00:06, 5.37it/s]\nDDIM Sampler: 36%|███▌ | 18/50 [00:09<00:05, 5.42it/s]\nDDIM Sampler: 38%|███▊ | 19/50 [00:09<00:05, 5.46it/s]\nDDIM Sampler: 40%|████ | 20/50 [00:09<00:05, 5.49it/s]\nDDIM Sampler: 42%|████▏ | 21/50 [00:10<00:05, 5.51it/s]\nDDIM Sampler: 44%|████▍ | 22/50 [00:10<00:05, 5.53it/s]\nDDIM Sampler: 46%|████▌ | 23/50 [00:10<00:04, 5.54it/s]\nDDIM Sampler: 48%|████▊ | 24/50 [00:10<00:04, 5.55it/s]\nDDIM Sampler: 50%|█████ | 25/50 [00:10<00:04, 5.55it/s]\nDDIM Sampler: 52%|█████▏ | 26/50 [00:11<00:04, 5.56it/s]\nDDIM Sampler: 54%|█████▍ | 27/50 [00:11<00:04, 5.56it/s]\nDDIM Sampler: 56%|█████▌ | 28/50 [00:11<00:03, 5.56it/s]\nDDIM Sampler: 58%|█████▊ | 29/50 [00:11<00:03, 5.56it/s]\nDDIM Sampler: 60%|██████ | 30/50 [00:11<00:03, 5.56it/s]\nDDIM Sampler: 62%|██████▏ | 31/50 [00:11<00:03, 5.56it/s]\nDDIM Sampler: 64%|██████▍ | 32/50 [00:12<00:03, 5.48it/s]\nDDIM Sampler: 66%|██████▌ | 33/50 [00:12<00:03, 5.50it/s]\nDDIM Sampler: 68%|██████▊ | 34/50 [00:12<00:02, 5.44it/s]\nDDIM Sampler: 70%|███████ | 35/50 [00:12<00:02, 5.23it/s]\nDDIM Sampler: 72%|███████▏ | 36/50 [00:12<00:02, 5.08it/s]\nDDIM Sampler: 74%|███████▍ | 37/50 [00:13<00:02, 4.99it/s]\nDDIM Sampler: 76%|███████▌ | 38/50 [00:13<00:02, 4.85it/s]\nDDIM Sampler: 78%|███████▊ | 39/50 [00:13<00:02, 4.74it/s]\nDDIM Sampler: 80%|████████ | 40/50 [00:13<00:02, 4.71it/s]\nDDIM Sampler: 82%|████████▏ | 41/50 [00:13<00:01, 4.69it/s]\nDDIM Sampler: 84%|████████▍ | 42/50 [00:14<00:01, 4.68it/s]\nDDIM Sampler: 86%|████████▌ | 43/50 [00:14<00:01, 4.68it/s]\nDDIM Sampler: 88%|████████▊ | 44/50 [00:14<00:01, 4.81it/s]\nDDIM Sampler: 90%|█████████ | 45/50 [00:14<00:00, 5.01it/s]\nDDIM Sampler: 92%|█████████▏| 46/50 [00:14<00:00, 5.16it/s]\nDDIM Sampler: 94%|█████████▍| 47/50 [00:15<00:00, 5.28it/s]\nDDIM Sampler: 96%|█████████▌| 48/50 [00:15<00:00, 5.36it/s]\nDDIM Sampler: 98%|█████████▊| 49/50 [00:15<00:00, 5.42it/s]\nDDIM Sampler: 100%|██████████| 50/50 [00:15<00:00, 5.46it/s]\nDDIM Sampler: 100%|██████████| 50/50 [00:15<00:00, 3.19it/s]",
"error": null,
"metrics": {
"predict_time": 32.909901,
"total_time": 121.483254
},
"created_at": "2023-09-20T19:17:04.700648Z",
"started_at": "2023-09-20T19:18:33.274001Z",
"completed_at": "2023-09-20T19:19:06.183902Z",
"urls": {
"get": "https://api.replicate.com/v1/predictions/qqynzilbxm2t5h6eaywx2p7g54",
"cancel": "https://api.replicate.com/v1/predictions/qqynzilbxm2t5h6eaywx2p7g54/cancel"
}
},
"latest_version": {
"id": "9c3d3e39fb0cb6aea677264881d8073f835336137b39fdea4e94093319379535",
"created_at": "2023-09-20T19:16:29.474130+00:00",
"cog_version": "0.8.6",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"required": [
"input_file"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 3,
"description": "Random seed. Leave blank to randomize the seed"
},
"ddim_steps": {
"type": "integer",
"title": "Ddim Steps",
"default": 50,
"maximum": 500,
"minimum": 10,
"x-order": 1,
"description": "Number of inference steps"
},
"input_file": {
"type": "string",
"title": "Input File",
"format": "uri",
"x-order": 0,
"description": "Audio to upsample"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 3.5,
"maximum": 20,
"minimum": 1,
"x-order": 2,
"description": "Scale for classifier free guidance"
}
}
},
"Output": {
"type": "string",
"title": "Output",
"format": "uri"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"start",
"output",
"logs",
"completed"
]
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
}
}
}
}
}
}
File diff suppressed because one or more lines are too long
+9 -2
View File
@@ -34,8 +34,8 @@
}
},
"latest_version": {
"id": "bc479d7d8ecc50eb83839af0c28210db75cac9c23837e2722028df4cddfafa22",
"created_at": "2024-06-29T14:40:18.046009+00:00",
"id": "1251f6b5b8c3ce671f937d1262cc7d542b7729c30ae5e67a4bf0eef61fdb8d82",
"created_at": "2024-07-02T11:05:12.162271+00:00",
"cog_version": "0.9.4",
"openapi_schema": {
"info": {
@@ -275,6 +275,13 @@
"format": "uri",
"x-order": 0,
"description": "Target/base image"
},
"disable_safety_checker": {
"type": "boolean",
"title": "Disable Safety Checker",
"default": false,
"x-order": 2,
"description": "Disable safety checker for swapped images"
}
}
},
+639
View File
@@ -0,0 +1,639 @@
{
"url": "https://replicate.com/suno-ai/bark",
"owner": "suno-ai",
"name": "bark",
"description": "🔊 Text-Prompted Generative Audio Model",
"visibility": "public",
"github_url": "https://github.com/chenxwh/bark",
"paper_url": null,
"license_url": "https://github.com/suno-ai/bark/blob/main/LICENSE",
"run_count": 0,
"cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/9fbbe7c2-beb0-4caa-bd59-647dd7eeee6b/fofr_dog.jpg",
"default_example": {
"completed_at": "2024-07-02T16:14:42.860493Z",
"created_at": "2024-07-02T16:14:01.017000Z",
"data_removed": false,
"error": null,
"id": "cvtnvmkn75rg80cgegws2aszp0",
"input": {
"prompt": "Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.",
"text_temp": 0.7,
"output_full": false,
"waveform_temp": 0.7,
"history_prompt": "announcer"
},
"logs": "0%| | 0/100 [00:00<?, ?it/s]\n 1%| | 1/100 [00:00<00:13, 7.39it/s]\n 3%|▎ | 3/100 [00:00<00:10, 9.39it/s]\n 5%|▌ | 5/100 [00:00<00:09, 10.34it/s]\n 7%|▋ | 7/100 [00:00<00:08, 10.36it/s]\n 9%|▉ | 9/100 [00:00<00:08, 10.66it/s]\n 11%|█ | 11/100 [00:01<00:08, 10.68it/s]\n 13%|█▎ | 13/100 [00:01<00:08, 10.80it/s]\n 15%|█▌ | 15/100 [00:01<00:07, 11.03it/s]\n 17%|█▋ | 17/100 [00:01<00:07, 11.17it/s]\n 19%|█▉ | 19/100 [00:01<00:07, 10.88it/s]\n 21%|██ | 21/100 [00:01<00:07, 10.98it/s]\n 23%|██▎ | 23/100 [00:02<00:06, 11.10it/s]\n 25%|██▌ | 25/100 [00:02<00:06, 10.82it/s]\n 27%|██▋ | 27/100 [00:02<00:06, 11.00it/s]\n 29%|██▉ | 29/100 [00:02<00:06, 10.92it/s]\n 31%|███ | 31/100 [00:02<00:06, 10.89it/s]\n 33%|███▎ | 33/100 [00:03<00:05, 11.23it/s]\n 35%|███▌ | 35/100 [00:03<00:05, 11.27it/s]\n 37%|███▋ | 37/100 [00:03<00:05, 10.96it/s]\n 39%|███▉ | 39/100 [00:03<00:05, 11.00it/s]\n 41%|████ | 41/100 [00:03<00:05, 10.90it/s]\n 43%|████▎ | 43/100 [00:03<00:05, 11.06it/s]\n 45%|████▌ | 45/100 [00:04<00:04, 11.12it/s]\n 47%|████▋ | 47/100 [00:04<00:04, 10.79it/s]\n 49%|████▉ | 49/100 [00:04<00:04, 10.82it/s]\n 51%|█████ | 51/100 [00:04<00:04, 10.78it/s]\n 53%|█████▎ | 53/100 [00:04<00:04, 10.71it/s]\n 55%|█████▌ | 55/100 [00:05<00:04, 10.97it/s]\n 57%|█████▋ | 57/100 [00:05<00:03, 11.12it/s]\n 59%|█████▉ | 59/100 [00:05<00:03, 10.85it/s]\n 61%|██████ | 61/100 [00:05<00:03, 10.83it/s]\n 63%|██████▎ | 63/100 [00:05<00:03, 10.73it/s]\n 65%|██████▌ | 65/100 [00:05<00:03, 10.90it/s]\n 67%|██████▋ | 67/100 [00:06<00:02, 11.01it/s]\n 69%|██████▉ | 69/100 [00:06<00:02, 10.86it/s]\n 71%|███████ | 71/100 [00:06<00:02, 10.71it/s]\n 73%|███████▎ | 73/100 [00:06<00:02, 10.64it/s]\n 75%|███████▌ | 75/100 [00:06<00:02, 10.25it/s]\n 77%|███████▋ | 77/100 [00:07<00:02, 10.47it/s]\n 79%|███████▉ | 79/100 [00:07<00:01, 10.54it/s]\n 81%|████████ | 81/100 [00:07<00:01, 10.42it/s]\n 83%|████████▎ | 83/100 [00:07<00:01, 10.11it/s]\n 85%|████████▌ | 85/100 [00:07<00:01, 10.23it/s]\n100%|██████████| 100/100 [00:07<00:00, 12.59it/s]\n 0%| | 0/33 [00:00<?, ?it/s]\n 3%|▎ | 1/33 [00:00<00:29, 1.08it/s]\n 6%|▌ | 2/33 [00:01<00:28, 1.08it/s]\n 9%|▉ | 3/33 [00:02<00:27, 1.09it/s]\n 12%|█▏ | 4/33 [00:03<00:26, 1.09it/s]\n 15%|█▌ | 5/33 [00:04<00:26, 1.07it/s]\n 18%|█▊ | 6/33 [00:05<00:25, 1.08it/s]\n 21%|██ | 7/33 [00:06<00:24, 1.08it/s]\n 24%|██▍ | 8/33 [00:07<00:23, 1.08it/s]\n 27%|██▋ | 9/33 [00:08<00:22, 1.09it/s]\n 30%|███ | 10/33 [00:09<00:21, 1.09it/s]\n 33%|███▎ | 11/33 [00:10<00:20, 1.09it/s]\n 36%|███▋ | 12/33 [00:11<00:19, 1.08it/s]\n 39%|███▉ | 13/33 [00:12<00:18, 1.08it/s]\n 42%|████▏ | 14/33 [00:12<00:17, 1.08it/s]\n 45%|████▌ | 15/33 [00:13<00:16, 1.08it/s]\n 48%|████▊ | 16/33 [00:14<00:15, 1.09it/s]\n 52%|█████▏ | 17/33 [00:15<00:14, 1.08it/s]\n 55%|█████▍ | 18/33 [00:16<00:13, 1.08it/s]\n 58%|█████▊ | 19/33 [00:17<00:12, 1.08it/s]\n 61%|██████ | 20/33 [00:18<00:12, 1.08it/s]\n 64%|██████▎ | 21/33 [00:19<00:11, 1.09it/s]\n 67%|██████▋ | 22/33 [00:20<00:10, 1.09it/s]\n 70%|██████▉ | 23/33 [00:21<00:09, 1.08it/s]\n 73%|███████▎ | 24/33 [00:22<00:08, 1.07it/s]\n 76%|███████▌ | 25/33 [00:23<00:07, 1.08it/s]\n 79%|███████▉ | 26/33 [00:24<00:06, 1.08it/s]\n 82%|████████▏ | 27/33 [00:25<00:05, 1.07it/s]\n 85%|████████▍ | 28/33 [00:25<00:04, 1.07it/s]\n 88%|████████▊ | 29/33 [00:26<00:03, 1.07it/s]\n 91%|█████████ | 30/33 [00:27<00:02, 1.07it/s]\n 94%|█████████▍| 31/33 [00:28<00:01, 1.06it/s]\n 97%|█████████▋| 32/33 [00:29<00:00, 1.06it/s]\n100%|██████████| 33/33 [00:30<00:00, 1.19it/s]\n100%|██████████| 33/33 [00:30<00:00, 1.09it/s]",
"metrics": {
"predict_time": 41.825636899,
"total_time": 41.843493
},
"output": {
"audio_out": "https://replicate.delivery/czjl/nLXd7G4BJjpXHtBNKsOn9WP6aKQn5NaL4mUGzogs45ucZHxE/audio.wav"
},
"started_at": "2024-07-02T16:14:01.034856Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/cvtnvmkn75rg80cgegws2aszp0",
"cancel": "https://api.replicate.com/v1/predictions/cvtnvmkn75rg80cgegws2aszp0/cancel"
},
"version": "b76242b40d67c76ab6742e987628a2a9ac019e11d56ab96c4e91ce03b79b2787"
},
"latest_version": {
"id": "b76242b40d67c76ab6742e987628a2a9ac019e11d56ab96c4e91ce03b79b2787",
"created_at": "2023-04-27T20:11:57.984157+00:00",
"cog_version": "0.7.0-beta19",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"properties": {
"prompt": {
"type": "string",
"title": "Prompt",
"default": "Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.",
"x-order": 0,
"description": "Input prompt"
},
"text_temp": {
"type": "number",
"title": "Text Temp",
"default": 0.7,
"x-order": 3,
"description": "generation temperature (1.0 more diverse, 0.0 more conservative)"
},
"output_full": {
"type": "boolean",
"title": "Output Full",
"default": false,
"x-order": 5,
"description": "return full generation as a .npz file to be used as a history prompt"
},
"waveform_temp": {
"type": "number",
"title": "Waveform Temp",
"default": 0.7,
"x-order": 4,
"description": "generation temperature (1.0 more diverse, 0.0 more conservative)"
},
"history_prompt": {
"allOf": [
{
"$ref": "#/components/schemas/history_prompt"
}
],
"x-order": 1,
"description": "history choice for audio cloning, choose from the list"
},
"custom_history_prompt": {
"type": "string",
"title": "Custom History Prompt",
"format": "uri",
"x-order": 2,
"description": "Provide your own .npz file with history choice for audio cloning, this will override the previous history_prompt setting"
}
}
},
"Output": {
"$ref": "#/components/schemas/ModelOutput",
"title": "Output"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"ModelOutput": {
"type": "object",
"title": "ModelOutput",
"required": [
"audio_out"
],
"properties": {
"audio_out": {
"type": "string",
"title": "Audio Out",
"format": "uri"
},
"prompt_npz": {
"type": "string",
"title": "Prompt Npz",
"format": "uri"
}
}
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"history_prompt": {
"enum": [
"announcer",
"de_speaker_0",
"de_speaker_1",
"de_speaker_2",
"de_speaker_3",
"de_speaker_4",
"de_speaker_5",
"de_speaker_6",
"de_speaker_7",
"de_speaker_8",
"de_speaker_9",
"en_speaker_0",
"en_speaker_1",
"en_speaker_2",
"en_speaker_3",
"en_speaker_4",
"en_speaker_5",
"en_speaker_6",
"en_speaker_7",
"en_speaker_8",
"en_speaker_9",
"es_speaker_0",
"es_speaker_1",
"es_speaker_2",
"es_speaker_3",
"es_speaker_4",
"es_speaker_5",
"es_speaker_6",
"es_speaker_7",
"es_speaker_8",
"es_speaker_9",
"fr_speaker_0",
"fr_speaker_1",
"fr_speaker_2",
"fr_speaker_3",
"fr_speaker_4",
"fr_speaker_5",
"fr_speaker_6",
"fr_speaker_7",
"fr_speaker_8",
"fr_speaker_9",
"hi_speaker_0",
"hi_speaker_1",
"hi_speaker_2",
"hi_speaker_3",
"hi_speaker_4",
"hi_speaker_5",
"hi_speaker_6",
"hi_speaker_7",
"hi_speaker_8",
"hi_speaker_9",
"it_speaker_0",
"it_speaker_1",
"it_speaker_2",
"it_speaker_3",
"it_speaker_4",
"it_speaker_5",
"it_speaker_6",
"it_speaker_7",
"it_speaker_8",
"it_speaker_9",
"ja_speaker_0",
"ja_speaker_1",
"ja_speaker_2",
"ja_speaker_3",
"ja_speaker_4",
"ja_speaker_5",
"ja_speaker_6",
"ja_speaker_7",
"ja_speaker_8",
"ja_speaker_9",
"ko_speaker_0",
"ko_speaker_1",
"ko_speaker_2",
"ko_speaker_3",
"ko_speaker_4",
"ko_speaker_5",
"ko_speaker_6",
"ko_speaker_7",
"ko_speaker_8",
"ko_speaker_9",
"pl_speaker_0",
"pl_speaker_1",
"pl_speaker_2",
"pl_speaker_3",
"pl_speaker_4",
"pl_speaker_5",
"pl_speaker_6",
"pl_speaker_7",
"pl_speaker_8",
"pl_speaker_9",
"pt_speaker_0",
"pt_speaker_1",
"pt_speaker_2",
"pt_speaker_3",
"pt_speaker_4",
"pt_speaker_5",
"pt_speaker_6",
"pt_speaker_7",
"pt_speaker_8",
"pt_speaker_9",
"ru_speaker_0",
"ru_speaker_1",
"ru_speaker_2",
"ru_speaker_3",
"ru_speaker_4",
"ru_speaker_5",
"ru_speaker_6",
"ru_speaker_7",
"ru_speaker_8",
"ru_speaker_9",
"tr_speaker_0",
"tr_speaker_1",
"tr_speaker_2",
"tr_speaker_3",
"tr_speaker_4",
"tr_speaker_5",
"tr_speaker_6",
"tr_speaker_7",
"tr_speaker_8",
"tr_speaker_9",
"zh_speaker_0",
"zh_speaker_1",
"zh_speaker_2",
"zh_speaker_3",
"zh_speaker_4",
"zh_speaker_5",
"zh_speaker_6",
"zh_speaker_7",
"zh_speaker_8",
"zh_speaker_9"
],
"type": "string",
"title": "history_prompt",
"description": "An enumeration."
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"completed",
"logs",
"output",
"start"
],
"uniqueItems": true
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
}
}
}
}
}
}
+655
View File
@@ -0,0 +1,655 @@
{
"url": "https://replicate.com/zsxkib/realistic-voice-cloning",
"owner": "zsxkib",
"name": "realistic-voice-cloning",
"description": "Create song covers with any RVC v2 trained AI voice from audio files.",
"visibility": "public",
"github_url": "https://github.com/zsxkib/AICoverGen.git",
"paper_url": null,
"license_url": "https://github.com/SociallyIneptWeeb/AICoverGen/blob/main/LICENSE",
"run_count": 0,
"cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/7a110507-8a38-4fcb-8826-61aec80309cb/Out_0_1024x1024.png",
"default_example": {
"id": "opfbdorbymurmp2ykemgwe23qa",
"model": "zsxkib/realistic-voice-cloning",
"version": "a0076ea13a704d9fa6d02535bc8951d3b141c84dc95d2d3f2f5016eabfcb8d94",
"status": "succeeded",
"input": {
"protect": 0.33,
"rvc_model": "Squidward",
"index_rate": 0.5,
"song_input": "https://replicate.delivery/pbxt/JsPIizFfRy54Jk5LuXdnrNdV1JHJ6oLmPPdRuIfh3lvpoNai/gangnam.mp3",
"reverb_size": 0.15,
"pitch_change": "no-change",
"rms_mix_rate": 0.25,
"filter_radius": 3,
"output_format": "mp3",
"reverb_damping": 0.7,
"reverb_dryness": 0.8,
"reverb_wetness": 0.2,
"crepe_hop_length": 128,
"pitch_change_all": 0,
"main_vocals_volume_change": 10,
"pitch_detection_algorithm": "rmvpe",
"instrumental_volume_change": 0,
"backup_vocals_volume_change": 0
},
"output": "https://replicate.delivery/pbxt/TqYjsueAmlVePUapV0rf7MCDCDBfAJxhw2aE5euzA6Gw4rCPC/tmp11cudxj_gangnam%20%28Squidward%20Ver%29.mp3",
"logs": "[~] Starting AI Cover Generation Pipeline...\n[~] Applying audio effects to Vocals...\n[~] Combining AI Vocals and Instrumentals...\n[~] Removing intermediate audio files...\n[+] Cover generated at /src/song_output/d0386572142/tmp11cudxj_gangnam (Squidward Ver).mp3",
"error": null,
"metrics": {
"predict_time": 2.811273,
"total_time": 2.832374
},
"created_at": "2023-11-14T16:52:20.000859Z",
"started_at": "2023-11-14T16:52:20.021960Z",
"completed_at": "2023-11-14T16:52:22.833233Z",
"urls": {
"get": "https://api.replicate.com/v1/predictions/opfbdorbymurmp2ykemgwe23qa",
"cancel": "https://api.replicate.com/v1/predictions/opfbdorbymurmp2ykemgwe23qa/cancel"
}
},
"latest_version": {
"id": "0a9c7c558af4c0f20667c1bd1260ce32a2879944a0b9e44e1398660c077b1550",
"created_at": "2023-11-15T16:00:55.551923+00:00",
"cog_version": "0.8.6",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"properties": {
"protect": {
"type": "number",
"title": "Protect",
"default": 0.33,
"maximum": 0.5,
"minimum": 0,
"x-order": 9,
"description": "Control how much of the original vocals' breath and voiceless consonants to leave in the AI vocals. Set 0.5 to disable."
},
"rvc_model": {
"allOf": [
{
"$ref": "#/components/schemas/rvc_model"
}
],
"default": "Squidward",
"x-order": 1,
"description": "RVC model for a specific voice. If using a custom model, this should match the name of the downloaded model. If a 'custom_rvc_model_download_url' is provided, this will be automatically set to the name of the downloaded model."
},
"index_rate": {
"type": "number",
"title": "Index Rate",
"default": 0.5,
"maximum": 1,
"minimum": 0,
"x-order": 4,
"description": "Control how much of the AI's accent to leave in the vocals."
},
"song_input": {
"type": "string",
"title": "Song Input",
"format": "uri",
"x-order": 0,
"description": "Upload your audio file here."
},
"reverb_size": {
"type": "number",
"title": "Reverb Size",
"default": 0.15,
"maximum": 1,
"minimum": 0,
"x-order": 14,
"description": "The larger the room, the longer the reverb time."
},
"pitch_change": {
"allOf": [
{
"$ref": "#/components/schemas/pitch_change"
}
],
"default": "no-change",
"x-order": 3,
"description": "Adjust pitch of AI vocals. Options: `no-change`, `male-to-female`, `female-to-male`."
},
"rms_mix_rate": {
"type": "number",
"title": "Rms Mix Rate",
"default": 0.25,
"maximum": 1,
"minimum": 0,
"x-order": 6,
"description": "Control how much to use the original vocal's loudness (0) or a fixed loudness (1)."
},
"filter_radius": {
"type": "integer",
"title": "Filter Radius",
"default": 3,
"maximum": 7,
"minimum": 0,
"x-order": 5,
"description": "If >=3: apply median filtering median filtering to the harvested pitch results."
},
"output_format": {
"allOf": [
{
"$ref": "#/components/schemas/output_format"
}
],
"default": "mp3",
"x-order": 18,
"description": "wav for best quality and large file size, mp3 for decent quality and small file size."
},
"reverb_damping": {
"type": "number",
"title": "Reverb Damping",
"default": 0.7,
"maximum": 1,
"minimum": 0,
"x-order": 17,
"description": "Absorption of high frequencies in the reverb."
},
"reverb_dryness": {
"type": "number",
"title": "Reverb Dryness",
"default": 0.8,
"maximum": 1,
"minimum": 0,
"x-order": 16,
"description": "Level of AI vocals without reverb."
},
"reverb_wetness": {
"type": "number",
"title": "Reverb Wetness",
"default": 0.2,
"maximum": 1,
"minimum": 0,
"x-order": 15,
"description": "Level of AI vocals with reverb."
},
"crepe_hop_length": {
"type": "integer",
"title": "Crepe Hop Length",
"default": 128,
"x-order": 8,
"description": "When `pitch_detection_algo` is set to `mangio-crepe`, this controls how often it checks for pitch changes in milliseconds. Lower values lead to longer conversions and higher risk of voice cracks, but better pitch accuracy."
},
"pitch_change_all": {
"type": "number",
"title": "Pitch Change All",
"default": 0,
"x-order": 13,
"description": "Change pitch/key of background music, backup vocals and AI vocals in semitones. Reduces sound quality slightly."
},
"main_vocals_volume_change": {
"type": "number",
"title": "Main Vocals Volume Change",
"default": 0,
"x-order": 10,
"description": "Control volume of main AI vocals. Use -3 to decrease the volume by 3 decibels, or 3 to increase the volume by 3 decibels."
},
"pitch_detection_algorithm": {
"allOf": [
{
"$ref": "#/components/schemas/pitch_detection_algorithm"
}
],
"default": "rmvpe",
"x-order": 7,
"description": "Best option is rmvpe (clarity in vocals), then mangio-crepe (smoother vocals)."
},
"instrumental_volume_change": {
"type": "number",
"title": "Instrumental Volume Change",
"default": 0,
"x-order": 12,
"description": "Control volume of the background music/instrumentals."
},
"backup_vocals_volume_change": {
"type": "number",
"title": "Backup Vocals Volume Change",
"default": 0,
"x-order": 11,
"description": "Control volume of backup AI vocals."
},
"custom_rvc_model_download_url": {
"type": "string",
"title": "Custom Rvc Model Download Url",
"x-order": 2,
"description": "URL to download a custom RVC model. If provided, the model will be downloaded (if it doesn't already exist) and used for prediction, regardless of the 'rvc_model' value."
}
}
},
"Output": {
"type": "string",
"title": "Output",
"format": "uri"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"rvc_model": {
"enum": [
"Squidward",
"MrKrabs",
"Plankton",
"Drake",
"Vader",
"Trump",
"Biden",
"Obama",
"Guitar",
"Voilin",
"CUSTOM"
],
"type": "string",
"title": "rvc_model",
"description": "An enumeration."
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"pitch_change": {
"enum": [
"no-change",
"male-to-female",
"female-to-male"
],
"type": "string",
"title": "pitch_change",
"description": "An enumeration."
},
"output_format": {
"enum": [
"mp3",
"wav"
],
"type": "string",
"title": "output_format",
"description": "An enumeration."
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"start",
"output",
"logs",
"completed"
]
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
},
"pitch_detection_algorithm": {
"enum": [
"rmvpe",
"mangio-crepe"
],
"type": "string",
"title": "pitch_detection_algorithm",
"description": "An enumeration."
}
}
}
}
}
}
+9
View File
@@ -1,5 +1,14 @@
{
"models": [
"suno-ai/bark",
"meta/musicgen",
"lucataco/magnet",
"nateraw/musicgen-songstarter-v0.2",
"nateraw/audio-super-resolution",
"zsxkib/realistic-voice-cloning",
"lucataco/xtts-v2",
"declare-lab/tango",
"cjwbw/seamless_communication",
"ai-forever/kandinsky-2.2",
"ai-forever/kandinsky-2",
"andreasjansson/blip-2",