110 lines
2.6 KiB
JSON
110 lines
2.6 KiB
JSON
{
|
|
"family": "vibevoice",
|
|
"display_name": "VibeVoice",
|
|
"description": "Microsoft long-form multi-speaker TTS model for expressive conversational audio such as podcasts, supporting up to 90 minutes of speech with as many as four speakers.",
|
|
"category": "tts",
|
|
"status": "supported",
|
|
"tasks": [
|
|
"tts"
|
|
],
|
|
"modes": [
|
|
"offline"
|
|
],
|
|
"languages": [
|
|
"en",
|
|
"zh"
|
|
],
|
|
"capabilities": {
|
|
"tts": [
|
|
"multi_speaker",
|
|
"long_form"
|
|
]
|
|
},
|
|
"runtime": {
|
|
"tags": [
|
|
"gguf"
|
|
]
|
|
},
|
|
"ui": {
|
|
"recommended_package": "vibevoice_1_5b_q8_0",
|
|
"tags": [
|
|
"TTS",
|
|
"GGUF"
|
|
],
|
|
"docs": [
|
|
"docs/tts.md",
|
|
"docs/gguf.md"
|
|
]
|
|
},
|
|
"package_defaults": {
|
|
"download": {
|
|
"kind": "huggingface_snapshot",
|
|
"repo": "audio-cpp/audio.cpp-gguf",
|
|
"revision": "main",
|
|
"gated": false
|
|
}
|
|
},
|
|
"packages": [
|
|
{
|
|
"id": "vibevoice_1_5b_q8_0",
|
|
"display_name": "VibeVoice 1.5B Q8_0 GGUF",
|
|
"default": true,
|
|
"format": "gguf",
|
|
"precision": "q8_0",
|
|
"target_directory": "VibeVoice-1.5B-GGUF",
|
|
"files": [
|
|
"VibeVoice-1.5B-GGUF/vibevoice-1.5b-q8_0.gguf"
|
|
],
|
|
"strip_prefix": "VibeVoice-1.5B-GGUF"
|
|
},
|
|
{
|
|
"id": "vibevoice_1_5b_bf16",
|
|
"display_name": "VibeVoice 1.5B BF16 GGUF",
|
|
"format": "gguf",
|
|
"precision": "bf16",
|
|
"target_directory": "VibeVoice-1.5B-GGUF",
|
|
"files": [
|
|
"VibeVoice-1.5B-GGUF/vibevoice-1.5b-bf16.gguf"
|
|
],
|
|
"strip_prefix": "VibeVoice-1.5B-GGUF"
|
|
}
|
|
],
|
|
"sources": [
|
|
{
|
|
"format": "gguf",
|
|
"roots": {
|
|
"model": ".",
|
|
"weights": "$gguf"
|
|
},
|
|
"files": {
|
|
"config": "model:config.json",
|
|
"preprocessor_config": "model:preprocessor_config.json",
|
|
"tokenizer_config": "model:tokenizer_config.json",
|
|
"tokenizer_json": "model:tokenizer.json",
|
|
"tokenizer_vocab": "model:vocab.json",
|
|
"tokenizer_merges": "model:merges.txt"
|
|
},
|
|
"tensors": {
|
|
"model_weights": "weights:"
|
|
}
|
|
},
|
|
{
|
|
"format": "safetensors",
|
|
"roots": {
|
|
"model": "."
|
|
},
|
|
"files": {
|
|
"config": "model:config.json",
|
|
"preprocessor_config": "model:preprocessor_config.json",
|
|
"tokenizer_config": "model:tokenizer_config.json",
|
|
"tokenizer_json": "model:tokenizer.json",
|
|
"tokenizer_vocab": "model:vocab.json",
|
|
"tokenizer_merges": "model:merges.txt"
|
|
},
|
|
"tensors": {
|
|
"model_weights": "model:model.safetensors.index.json"
|
|
}
|
|
}
|
|
]
|
|
}
|