Views
No views yet
synthetic_ft_80_best_vocos_int8.onnx - best validation checkpoint exported as a single embedded-Vocos ONNX model with dynamic int8 quantization.synthetic_ft_80_latest_vocos_fp32.onnx - latest checkpoint exported as a single fp32 ONNX model with embedded Vocos vocoder. Outputs waveform audio directly.synthetic_ft_80_latest_hifigan_fp32.onnx - latest checkpoint exported as a single fp32 ONNX model with embedded official LJ HiFi-GAN V1 vocoder. Outputs waveform audio directly.best.pth - PyTorch training checkpoint for the best validation loss checkpoint.1from mixer_tts_onnx import MixerTTS
2
3tts = MixerTTS("synthetic_ft_80_latest_vocos_fp32.onnx")
4tts.create(
5 "sˈimu lˈev nosʔˈim jekaʁˈim.",
6 is_phonemes=True,
7 output_path="sample.wav",
8)is_phonemes=True. For plain English text it can phonemize with eSpeak; Hebrew should be passed as IPA phonemes.best.pth by validation loss; latest files are exported from the latest training last.pth at upload time.1@article{Tatanov2021MixerTTSNF,
2 title={Mixer-TTS: Non-Autoregressive, Fast and Compact Text-to-Speech Model Conditioned on Language Model Embeddings},
3 author={Oktai Tatanov and Stanislav Beliaev and Boris Ginsburg},
4 journal={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
5 year={2021},
6 pages={7482-7486},
7}