nodes/royceschultz-ComfyUI-TranscriptionTools
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Adds documentation and example workflows.

Browse Source
This commit is contained in:
Royce Schultz
2024-04-21 21:51:55 -06:00
parent e430275587
commit 197beededa
7 changed files with 508 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -2
View File
@@ -4,11 +4,16 @@ This package provides custom nodes for ComfyUI to perform transcription tasks on
<img src="assets/workflow_example.jpg" alt="isolated" width="800"/>
Note: To text (Debug) is part of [ComfyUI-Manager](https://github.com/ltdrdata/ComfyUI-Manager), but you probably have that installed already.
Note: To text (Debug) is part of [Derfuu_ModdedNodes](https://github.com/Derfuu/Derfuu_ComfyUI_ModdedNodes).
## Documentation
[See Docs](docs/README.md)
[Example Workflows](docs/workflows.md)
[Node Info](docs/nodes.md)
[Supported Transcription Models](docs/models.md)
## Special Thanks
docs/README.md
-5
View File
@@ -1,5 +0,0 @@
# ComfyUI Transcription Tools Docs
[Nodes](nodes.md)
[Supported Transcription Models](models.md)
docs/workflows.md
+18
View File
@@ -0,0 +1,18 @@
# Workflows
## Single Transcribe
Loads audio or video files from the `input/` folder. Saves the transcription to the `output/transcriptions` folder.
[single_transcribe.json](../workflows/single_transcribe.json)
<img src="../workflows/single_transcribe.jpg" alt="isolated" width="800"/>
## Batch Transcribe
Loads audio and video files from the selected folder. Folders may be selected relative to the `input/` or the system root. Saves the transcriptions to the `output/transcriptions` folder.
[batch_transcribe.json](../workflows/batch_transcribe.json)
<img src="../workflows/batch_transcribe.jpg" alt="isolated" width="800"/>
workflows/batch_transcribe.jpg
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 79 KiB

workflows/batch_transcribe.json
+252
View File
@@ -0,0 +1,252 @@
{
"last_node_id": 9,
"last_link_id": 7,
"nodes": [
{
"id": 1,
"type": "TT-LoadWhisperModel",
"pos": [
100,
100
],
"size": {
"0": 315,
"1": 82
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "pipeline",
"type": "TRANSCRIPTION_PIPELINE",
"links": [
4
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "TT-LoadWhisperModel"
},
"widgets_values": [
"openai/whisper-large-v3",
"en"
]
},
{
"id": 6,
"type": "TT-WhisperTranscriptionBatch",
"pos": [
475,
100
],
"size": {
"0": 315,
"1": 198
},
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "pipeline",
"type": "TRANSCRIPTION_PIPELINE",
"link": 4
},
{
"name": "wav_bytes_batch",
"type": "WAV_BYTES_BATCH",
"link": 5
}
],
"properties": {
"Node name for S&R": "TT-WhisperTranscriptionBatch"
},
"widgets_values": [
true,
true,
true,
"demo_",
"",
true
]
},
{
"id": 7,
"type": "TT-LoadBatch",
"pos": [
100,
225
],
"size": {
"0": 315,
"1": 170
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "wav_bytes_batch",
"type": "WAV_BYTES_BATCH",
"links": [
5
],
"shape": 3,
"slot_index": 0
},
{
"name": "count",
"type": "INT",
"links": [
6
],
"shape": 3,
"slot_index": 1
},
{
"name": "filenames",
"type": "LIST[STRING]",
"links": [
7
],
"shape": 3,
"slot_index": 2
}
],
"properties": {
"Node name for S&R": "TT-LoadBatch"
},
"widgets_values": [
"input",
"",
"",
""
]
},
{
"id": 8,
"type": "To text (Debug)",
"pos": [
700,
350
],
"size": {
"0": 216.59999084472656,
"1": 96
},
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "ANY",
"type": "*",
"link": 6
}
],
"outputs": [
{
"name": "SAME AS INPUT",
"type": "*",
"links": null,
"shape": 3
},
{
"name": "STRING",
"type": "STRING",
"links": null,
"shape": 6
}
],
"properties": {
"Node name for S&R": "To text (Debug)"
},
"widgets_values": [
"1"
]
},
{
"id": 9,
"type": "To text (Debug)",
"pos": [
475,
350
],
"size": {
"0": 216.59999084472656,
"1": 96
},
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "ANY",
"type": "*",
"link": 7
}
],
"outputs": [
{
"name": "SAME AS INPUT",
"type": "*",
"links": null,
"shape": 3
},
{
"name": "STRING",
"type": "STRING",
"links": null,
"shape": 6
}
],
"properties": {
"Node name for S&R": "To text (Debug)"
},
"widgets_values": [
"['bho_2014_1120_ImmigrationSpeech.mp4']"
]
}
],
"links": [
[
4,
1,
0,
6,
0,
"TRANSCRIPTION_PIPELINE"
],
[
5,
7,
0,
6,
1,
"WAV_BYTES_BATCH"
],
[
6,
7,
1,
8,
0,
"*"
],
[
7,
7,
2,
9,
0,
"*"
]
],
"groups": [],
"config": {},
"extra": {},
"version": 0.4
}
workflows/single_transcribe.jpg
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 145 KiB

workflows/single_transcribe.json
+231
View File
@@ -0,0 +1,231 @@
{
"last_node_id": 5,
"last_link_id": 3,
"nodes": [
{
"id": 1,
"type": "TT-LoadWhisperModel",
"pos": [
100,
100
],
"size": {
"0": 315,
"1": 82
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "pipeline",
"type": "TRANSCRIPTION_PIPELINE",
"links": [
1
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "TT-LoadWhisperModel"
},
"widgets_values": [
"openai/whisper-large-v3",
"en"
]
},
{
"id": 3,
"type": "TT-WhisperTranscription",
"pos": [
475,
100
],
"size": {
"0": 315,
"1": 174
},
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "pipeline",
"type": "TRANSCRIPTION_PIPELINE",
"link": 1
},
{
"name": "wav_bytes",
"type": "WAV_BYTES",
"link": 2
}
],
"outputs": [
{
"name": "transcription",
"type": "STRING",
"links": [
3
],
"shape": 3,
"slot_index": 0
},
{
"name": "chunks",
"type": "STRING",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "TT-WhisperTranscription"
},
"widgets_values": [
true,
false,
false,
"transcription",
true
]
},
{
"id": 4,
"type": "To text (Debug)",
"pos": [
825,
100
],
"size": {
"0": 216.59999084472656,
"1": 96
},
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "ANY",
"type": "*",
"link": 3
}
],
"outputs": [
{
"name": "SAME AS INPUT",
"type": "*",
"links": null,
"shape": 3
},
{
"name": "STRING",
"type": "STRING",
"links": null,
"shape": 6
}
],
"properties": {
"Node name for S&R": "To text (Debug)"
},
"widgets_values": [
""
]
},
{
"id": 5,
"type": "TT-LoadAudio",
"pos": [
100,
225
],
"size": {
"0": 315,
"1": 58
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "wav_bytes",
"type": "WAV_BYTES",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "TT-LoadAudio"
},
"widgets_values": [
null
]
},
{
"id": 2,
"type": "TT-LoadVideoAudio",
"pos": [
100,
325
],
"size": {
"0": 315,
"1": 58
},
"flags": {},
"order": 2,
"mode": 0,
"outputs": [
{
"name": "wav_bytes",
"type": "WAV_BYTES",
"links": [
2
],
"shape": 3,
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "TT-LoadVideoAudio"
},
"widgets_values": [
"",
{
"hidden": false,
"paused": false,
"params": {}
}
]
}
],
"links": [
[
1,
1,
0,
3,
0,
"TRANSCRIPTION_PIPELINE"
],
[
2,
2,
0,
3,
1,
"WAV_BYTES"
],
[
3,
3,
0,
4,
0,
"*"
]
],
"groups": [],
"config": {},
"extra": {},
"version": 0.4
}