Inflect-Micro-v2-zh / models /model_meta.json
inoryQwQ's picture
Release 1.0.0: Chinese TTS (Inflect-Micro-v2 arch + BigVGAN), ONNX + AX650 axmodel + checkpoints
0c723b3 verified
Raw
History Blame Contribute Delete
2.13 kB
{
"name": "Inflect-Micro-v2-zh",
"version": "1.0.0",
"description": "Chinese TTS: text-to-mel acoustic model (6.7M) + NVIDIA BigVGAN vocoder",
"pipeline": ["text", "mel", "wav"],
"sampling_rate": 24000,
"mel": {
"n_mels": 100,
"n_fft": 1024,
"hop_length": 256,
"win_length": 1024,
"fmin": 0,
"fmax": 12000,
"style": "bigvgan"
},
"models": {
"acoustic_female.onnx": {
"role": "text->mel (female voice)",
"backend": "CPU (onnxruntime, fp32)",
"inputs": {
"x": "int64[1,256] token ids (with blanks, max 256)",
"x_lengths": "int64[1]",
"noise_z": "float32[1,192,1024]"
},
"outputs": {
"mel": "float32[1,100,1024] log-mel",
"y_lengths": "int32[1] valid mel frames"
},
"length_scale": 0.7,
"max_text": 256,
"max_mel": 1024
},
"acoustic_male.onnx": {
"role": "text->mel (male voice)",
"backend": "CPU (onnxruntime, fp32)",
"inputs": {
"x": "int64[1,256]",
"x_lengths": "int64[1]",
"noise_z": "float32[1,192,1024]"
},
"outputs": {
"mel": "float32[1,100,1024]",
"y_lengths": "int32[1]"
},
"length_scale": 0.85,
"max_text": 256,
"max_mel": 1024
},
"bigvgan_base.onnx": {
"role": "mel->wav (vocoder, dynamic frames)",
"backend": "CPU (onnxruntime, fp32)",
"inputs": {"mel": "float32[1,100,T]"},
"outputs": {"wav": "float32[1,1,T*256]"}
},
"bigvgan_base.axmodel": {
"role": "mel->wav (vocoder, AX650 NPU)",
"backend": "NPU (axengine, int8, AX650/NPU3)",
"inputs": {"mel": "float32[1,100,512]"},
"outputs": {"wav": "float32[1,1,131072]"},
"compiled_by": "Pulsar2 7.0"
}
},
"performance": {
"ax650_cpu_acoustic_seconds": 0.30,
"ax650_npu_vocoder_seconds_per_block": 0.30,
"rtf_mixed_cpu_npu": "0.15-0.19"
},
"license": "apache-2.0",
"acknowledgements": [
"Inflect-Micro-v2 (owensong, Apache-2.0)",
"NVIDIA BigVGAN (MIT)",
"FunAudioLLM CosyVoice (Apache-2.0)",
"OpenSLR AISHELL-3"
]
}