v0.0.12

🐸 v0.0.12

🐞Bug Fixes

• fix #419 (This is a crucial bug fix).
• fix #408

💾 Code updates

• Enable logging model config.json on Tensorboard. #418
• Update code style standards and use a Makefile to ease regular tasks. #423
• Enable using Tacotron.prenet.dropout at inference time. This leads to a better quality with some models.
• Update default tts model to LJspeech TacotronDDC.
• Show the real waveform on Tensorboard in GAN vocoder training.

🚶‍♀️ Operational Updates

🏅 Model implementations

• initial HiFiGAN implementation (:crown: @rishikksh20 @erogol) #422

🚀 New Pre-Trained Model Releases

• Universal HifiGAN model(postponed to the next version for 👑 @Edresson's updated model.)
• LJSpeech, Tacotron2 Double Decoder Consistency v2 model.
  Check our blog post to learn more about Double Decoder Consistency.
• LJSpeech HifiGAN model.

Released Models

💡 All the models below are available by tts end point as explained here.

Language	Dataset	Model Name	Model Type	TTS version	Download
✨ English	LJSpeech	Tacotron-DDC	tts	😃 v0.0.12	💾
German	Thorsten-DE	Tacotron-DCA	tts	v0.0.11	💾
German	Thorsten-DE	Wavegrad	vocoder	v0.0.11	💾
English	LJSpeech	SpeedySpeech	tts	v0.0.10	💾
English	EK1	Tacotron2	tts	v0.0.10	💾
Dutch	MAI	TacotronDDC	tts	v0.0.10	💾
Chinese	Baker	TacotronDDC-GST	tts	v0.0.10	💾
English	LJSpeech	TacotronDCA	tts	v0.0.9	💾
English	LJSpeech	Glow-TTS	tts	v0.0.9	💾
Spanish	M-AILabs	TacotronDDC	tts	v0.0.9	💾
French	M_AILabs	TacotronDDC	tts	v0.0.9	💾
Dutch	MAI	TacotronDDC	tts	v0.0.10	💾
✨ English	LJSpeech	HiFiGAN	vocoder	😃 v0.0.12	💾
English	EK1	WaveGrad	vocoder	v0.0.10	💾
Dutch	MAI	ParallelWaveGAN	vocoder	v0.0.10	💾
English	LJSpeech	MB-MelGAN	vocoder	v0.0.9	💾
🌍 Multi-Lang	LibriTTS	FullBand-MelGAN	vocoder	v0.0.9	💾
🌍 Multi-Lang	LibriTTS	WaveGrad	vocoder	v0.0.9	💾