112 lines
2.6 KiB
JSON
112 lines
2.6 KiB
JSON
{
|
|
"family": "fish_audio",
|
|
"display_name": "Fish Audio S2 Pro",
|
|
"description": "Fish Audio S2 Pro text-to-speech model for expressive speech across 80+ languages, with automatic language handling, inline prosody/emotion controls, and rapid voice cloning from short reference samples.",
|
|
"category": "tts",
|
|
"status": "supported",
|
|
"tasks": [
|
|
"tts",
|
|
"clone"
|
|
],
|
|
"modes": [
|
|
"offline"
|
|
],
|
|
"languages": [
|
|
"80+ languages"
|
|
],
|
|
"capabilities": {
|
|
"clone": [
|
|
"speaker_reference"
|
|
]
|
|
},
|
|
"runtime": {
|
|
"tags": [
|
|
"gguf"
|
|
]
|
|
},
|
|
"ui": {
|
|
"recommended_package": "fish_audio_s2_pro_q8_0",
|
|
"tags": [
|
|
"TTS",
|
|
"Clone",
|
|
"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": "fish_audio_s2_pro_q8_0",
|
|
"display_name": "Fish Audio S2 Pro Q8_0 GGUF",
|
|
"default": true,
|
|
"format": "gguf",
|
|
"precision": "q8_0",
|
|
"target_directory": "Fish-Audio-S2-Pro-GGUF",
|
|
"files": [
|
|
"Fish-Audio-S2-Pro-GGUF/fish-audio-s2-pro-q8_0.gguf"
|
|
],
|
|
"strip_prefix": "Fish-Audio-S2-Pro-GGUF"
|
|
},
|
|
{
|
|
"id": "fish_audio_s2_pro_bf16",
|
|
"display_name": "Fish Audio S2 Pro BF16 GGUF",
|
|
"format": "gguf",
|
|
"precision": "bf16",
|
|
"target_directory": "Fish-Audio-S2-Pro-GGUF",
|
|
"files": [
|
|
"Fish-Audio-S2-Pro-GGUF/fish-audio-s2-pro-bf16.gguf"
|
|
],
|
|
"strip_prefix": "Fish-Audio-S2-Pro-GGUF"
|
|
}
|
|
],
|
|
"sources": [
|
|
{
|
|
"format": "gguf",
|
|
"roots": {
|
|
"model": ".",
|
|
"weights": "$gguf"
|
|
},
|
|
"files": {
|
|
"config": "model:config.json",
|
|
"tokenizer_config": "model:tokenizer_config.json",
|
|
"tokenizer_json": "model:tokenizer.json"
|
|
},
|
|
"tensors": {
|
|
"model_weights": {
|
|
"source": "weights:",
|
|
"prefix": "model_weights"
|
|
},
|
|
"codec_weights": {
|
|
"source": "weights:",
|
|
"prefix": "codec_weights"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"format": "safetensors",
|
|
"roots": {
|
|
"model": "."
|
|
},
|
|
"files": {
|
|
"config": "model:config.json",
|
|
"tokenizer_config": "model:tokenizer_config.json",
|
|
"tokenizer_json": "model:tokenizer.json"
|
|
},
|
|
"tensors": {
|
|
"model_weights": "model:model_audio_cpp.safetensors.index.json",
|
|
"codec_weights": "model:codec.safetensors"
|
|
}
|
|
}
|
|
]
|
|
}
|