115 lines
2.7 KiB
JSON
115 lines
2.7 KiB
JSON
{
|
|
"family": "vibevoice_asr",
|
|
"display_name": "VibeVoice ASR",
|
|
"description": "Microsoft long-form speech-to-text model that processes up to 60 minutes of audio in one pass and produces structured transcripts with speakers, timestamps, content, hotwords, and 50+ language support.",
|
|
"category": "asr",
|
|
"status": "supported",
|
|
"tasks": [
|
|
"asr"
|
|
],
|
|
"modes": [
|
|
"offline"
|
|
],
|
|
"languages": [
|
|
"auto",
|
|
"51 languages"
|
|
],
|
|
"capabilities": {
|
|
"asr": [
|
|
"segments",
|
|
"speaker_turns",
|
|
"vad_chunking"
|
|
]
|
|
},
|
|
"runtime": {
|
|
"tags": [
|
|
"gguf"
|
|
]
|
|
},
|
|
"ui": {
|
|
"recommended_package": "vibevoice_asr_q8_0",
|
|
"tags": [
|
|
"ASR",
|
|
"GGUF"
|
|
],
|
|
"docs": [
|
|
"docs/asr.md",
|
|
"docs/gguf.md"
|
|
]
|
|
},
|
|
"package_defaults": {
|
|
"download": {
|
|
"kind": "huggingface_snapshot",
|
|
"repo": "audio-cpp/audio.cpp-gguf",
|
|
"revision": "main",
|
|
"gated": false
|
|
}
|
|
},
|
|
"packages": [
|
|
{
|
|
"id": "vibevoice_asr_q8_0",
|
|
"display_name": "VibeVoice ASR Q8_0 GGUF",
|
|
"default": true,
|
|
"format": "gguf",
|
|
"precision": "q8_0",
|
|
"target_directory": "VibeVoice-ASR-GGUF",
|
|
"files": [
|
|
"VibeVoice-ASR-GGUF/vibevoice-asr-q8_0.gguf"
|
|
],
|
|
"strip_prefix": "VibeVoice-ASR-GGUF"
|
|
},
|
|
{
|
|
"id": "vibevoice_asr_f16",
|
|
"display_name": "VibeVoice ASR F16 GGUF",
|
|
"format": "gguf",
|
|
"precision": "f16",
|
|
"target_directory": "VibeVoice-ASR-GGUF",
|
|
"files": [
|
|
"VibeVoice-ASR-GGUF/vibevoice-asr-f16.gguf"
|
|
],
|
|
"strip_prefix": "VibeVoice-ASR-GGUF"
|
|
}
|
|
],
|
|
"sources": [
|
|
{
|
|
"format": "gguf",
|
|
"roots": {
|
|
"model": ".",
|
|
"weights": "$gguf"
|
|
},
|
|
"files": {
|
|
"config": "model:config.json",
|
|
"tokenizer_config": "model:tokenizer_config.json",
|
|
"tokenizer_json": "model:tokenizer.json",
|
|
"tokenizer_vocab": "model:vocab.json",
|
|
"tokenizer_merges": "model:merges.txt"
|
|
},
|
|
"optional_files": {
|
|
"preprocessor_config": "model:preprocessor_config.json"
|
|
},
|
|
"tensors": {
|
|
"model_weights": "weights:"
|
|
}
|
|
},
|
|
{
|
|
"format": "safetensors",
|
|
"roots": {
|
|
"model": "."
|
|
},
|
|
"files": {
|
|
"config": "model:config.json",
|
|
"tokenizer_config": "model:tokenizer_config.json",
|
|
"tokenizer_json": "model:tokenizer.json",
|
|
"tokenizer_vocab": "model:vocab.json",
|
|
"tokenizer_merges": "model:merges.txt"
|
|
},
|
|
"optional_files": {
|
|
"preprocessor_config": "model:preprocessor_config.json"
|
|
},
|
|
"tensors": {
|
|
"model_weights": "model:model.safetensors.index.json"
|
|
}
|
|
}
|
|
]
|
|
}
|