150 lines
3.3 KiB
JSON
150 lines
3.3 KiB
JSON
{
|
|
"family": "moss_tts_local",
|
|
"display_name": "MOSS-TTS-Local",
|
|
"description": "Flagship MOSS-TTS model for high-fidelity 31-language and code-switched speech, zero-shot voice cloning, long-form generation, and fine-grained Pinyin, phoneme, and duration control.",
|
|
"category": "tts",
|
|
"status": "supported",
|
|
"tasks": [
|
|
"tts",
|
|
"clone"
|
|
],
|
|
"modes": [
|
|
"offline"
|
|
],
|
|
"languages": [
|
|
"ar",
|
|
"cs",
|
|
"da",
|
|
"de",
|
|
"el",
|
|
"en",
|
|
"es",
|
|
"fa",
|
|
"fi",
|
|
"fr",
|
|
"he",
|
|
"hi",
|
|
"hu",
|
|
"it",
|
|
"ja",
|
|
"ko",
|
|
"mk",
|
|
"ms",
|
|
"nl",
|
|
"pl",
|
|
"pt",
|
|
"ro",
|
|
"ru",
|
|
"sv",
|
|
"sw",
|
|
"th",
|
|
"tl",
|
|
"tr",
|
|
"vi",
|
|
"yue",
|
|
"zh"
|
|
],
|
|
"capabilities": {
|
|
"clone": [
|
|
"speaker_reference"
|
|
]
|
|
},
|
|
"runtime": {
|
|
"tags": [
|
|
"gguf"
|
|
]
|
|
},
|
|
"ui": {
|
|
"recommended_package": "moss_tts_local_v1_5_q8_0",
|
|
"tags": [
|
|
"TTS",
|
|
"Clone",
|
|
"GGUF"
|
|
],
|
|
"docs": [
|
|
"docs/models/moss_tts.md",
|
|
"docs/tts.md",
|
|
"docs/gguf.md"
|
|
]
|
|
},
|
|
"package_defaults": {
|
|
"download": {
|
|
"kind": "huggingface_snapshot",
|
|
"repo": "audio-cpp/audio.cpp-gguf",
|
|
"revision": "main",
|
|
"gated": false
|
|
}
|
|
},
|
|
"packages": [
|
|
{
|
|
"id": "moss_tts_local_v1_5_q8_0",
|
|
"display_name": "MOSS-TTS-Local v1.5 Q8_0 GGUF",
|
|
"default": true,
|
|
"format": "gguf",
|
|
"precision": "q8_0",
|
|
"target_directory": "MOSS-TTS-Local-v1.5-GGUF",
|
|
"files": [
|
|
"MOSS-TTS-Local-v1.5-GGUF/moss-tts-local-v1.5-q8_0.gguf"
|
|
],
|
|
"strip_prefix": "MOSS-TTS-Local-v1.5-GGUF"
|
|
},
|
|
{
|
|
"id": "moss_tts_local_v1_5_bf16",
|
|
"display_name": "MOSS-TTS-Local v1.5 BF16 GGUF",
|
|
"format": "gguf",
|
|
"precision": "bf16",
|
|
"target_directory": "MOSS-TTS-Local-v1.5-GGUF",
|
|
"files": [
|
|
"MOSS-TTS-Local-v1.5-GGUF/moss-tts-local-v1.5-bf16.gguf"
|
|
],
|
|
"strip_prefix": "MOSS-TTS-Local-v1.5-GGUF"
|
|
}
|
|
],
|
|
"sources": [
|
|
{
|
|
"format": "gguf",
|
|
"roots": {
|
|
"model": ".",
|
|
"weights": "$gguf"
|
|
},
|
|
"files": {
|
|
"config": "model:config.json",
|
|
"tokenizer_json": "model:tokenizer.json",
|
|
"tokenizer_config": "model:tokenizer_config.json",
|
|
"tokenizer_vocab": "model:vocab.json",
|
|
"tokenizer_merges": "model:merges.txt",
|
|
"audio_tokenizer_config": "model:audio_tokenizer/config.json"
|
|
},
|
|
"tensors": {
|
|
"model_weights": {
|
|
"source": "weights:",
|
|
"prefix": "model_weights"
|
|
},
|
|
"audio_tokenizer_weights": {
|
|
"source": "weights:",
|
|
"prefix": "audio_tokenizer_weights"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"format": "safetensors",
|
|
"roots": {
|
|
"model": ".",
|
|
"audio_tokenizer": "audio_tokenizer"
|
|
},
|
|
"files": {
|
|
"config": "model:config.json",
|
|
"tokenizer_json": "model:tokenizer.json",
|
|
"tokenizer_config": "model:tokenizer_config.json",
|
|
"tokenizer_vocab": "model:vocab.json",
|
|
"tokenizer_merges": "model:merges.txt",
|
|
"audio_tokenizer_config": "audio_tokenizer:config.json"
|
|
},
|
|
"tensors": {
|
|
"model_weights": "model:model.safetensors",
|
|
"audio_tokenizer_weights": "audio_tokenizer:model.safetensors.index.json"
|
|
}
|
|
}
|
|
]
|
|
}
|