9 open source projects by keonlee9420

PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supports both single-, multi-speaker TTS and several techniques to enforce the robustness and efficiency of the model.

✭ 22

python text-to-speech deep-learning efficiency pytorch tts speech-synthesis autoregressive multi-speaker robustness comprehensive tacotron single-speaker neural-tts tacotron2 reduction-factor hifi-gan mel-gan diagonal-guided-attention

2. Parallel-Tacotron2

PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling

✭ 149

python text-to-speech duration pytorch tts speech-synthesis english vae self-attention neural-tts non-autoregressive fastspeech parallel-tacotron parallel-tacotron2

3. STYLER

Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech, INTERSPEECH 2021

✭ 105

python shell fast text-to-speech tts style-transfer robust prosody expressive-speech-synthesis neural-text-to-speech style-modeling expressive-tts controllable-tts fast-tts robust-tts

4. WaveGrad2

PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

✭ 55

python audio text-to-speech duration end-to-end pytorch tts speech-synthesis robust synthesis neural-tts non-autoregressive text-to-audio score-matching phoneme-to-waveform

5. Daft-Exprt

PyTorch Implementation of Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis

✭ 41

python Dockerfile text-to-speech style pytorch tts speech-synthesis english speaker prosody neural-tts non-autoregressive prosody-transfer gaussian-upsampling

6. VAENAR-TTS

PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

✭ 66

python text-to-speech duration pytorch tts speech-synthesis vae unsupervised-learning glow self-attention neural-tts non-autoregressive transforer non-ar unsupervised-duration

7. Cross-Speaker-Emotion-Transfer

PyTorch Implementation of ByteDance's Cross-speaker Emotion Transfer Based on Speaker Condition Layer Normalization and Semi-Supervised Training in Text-To-Speech

✭ 107

python Dockerfile text-to-speech deep-neural-networks pytorch tts speech-synthesis generative-model semi-supervised-learning global-style-tokens neural-tts non-autoregressive parallel-tacotron non-ar emotion-transfer cross-speaker conditional-layer-normalization

8. Expressive-FastSpeech2

PyTorch Implementation of Non-autoregressive Expressive (emotional, conversational) TTS based on FastSpeech2, supporting English, Korean, and your own languages.

✭ 139

python text-to-speech tts speech-synthesis expressive-speech-synthesis non-autoregressive emotional-tts korean-tts expressive-tts emotional-speech-synthesis korean-speech-synthesis conversational-tts conversational-speech-synthesis

9. Soft-DTW-Loss

PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA

✭ 76

python deep-neural-networks deep-learning time-series dtw cuda pytorch dynamic-time-warping soft-dtw loss-function

1-9 of 9 user projects