There is a newer version of the record available.

Published August 11, 2021 | Version v0.2.0
Software Open

coqui-ai/TTS: v0.2.0

Authors/Creators

  • 1. Coqui.ai
  • 2. University of São Paulo (USP)
  • 3. Faculty of Electrical Engineering and Information Technologies
  • 4. University of Münster (WWU)
  • 5. no
  • 6. Open Source
  • 7. @Storytel
  • 8. Inveniem

Description

🐸 v0.2.0 🐞Bug Fixes
  • Fix phoneme pre-compute issue.
  • Fix multi-speaker setup in Tacotron models.
  • Fix small issues in the Trainer regarding multi-optimizer training.
💾 Code updates
  • W&B integration for model logging and experiment tracking, (👑 @AyushExel)
    Code uses the Tensorboard by default. For W&B, you need to set `log_dashboard` option in the config and define `project_name` and `wandb_entity`.
  • Use ffsspec for model saving/loading (👑 @agrinh)
  • Allow models to define their own symbol list with in-class make_symbols()
  • Allow choosing after epoch or after step LR scheduler update with scheduler_after_epoch.
  • Make converting spectrogram from amplitude to DB optional with do_amp_to_db_linear and do_amp_to_db_linear options.
🗒️ Docs updates
  • Add GlowTTS and VITS docs.
🤖 Model implementations 🚀 Model releases

  • vocoder_models--ja--kokoro--hifigan_v1 (👑 @kaiidams)

    HiFiGAN model trained on Kokoro dataset to complement the existing Japanese model.

    ### Try it out:

      tts --model_name vocoder_models--ja--kokoro--hifigan_v1 --text "こんにちは、今日はいい天気ですか?"

  • tts_models--en--ljspeech--tacotronDDC_ph

    TacotronDDC with phonemes trained on LJSpeech. It is to fix the pronunciation errors caused by the raw text in the released TacotronDDC model.

    ### Try it out:

      tts --model_name tts_models--en--ljspeech--tacotronDDC_ph --text "hello, how are you today?"

  • tts_models--en--ljspeech--vits

    VITS model trained on LJSpeech.

    ### Try it out:

      tts --model_name tts_models--en--ljspeech--vits --text "hello, how are you today?"

  • tts_models--en--vctk--vits

    VITS model trained on VCTK with multi-speaker support.

    ### Try it out:

      tts-server --model_name tts_models--en--vctk--vits --text "hello, how are you today?"

  • vocoder_models--en--ljspeech--univnet

    UnivNet model trained on LJSpeech to complement the TacotronDDC model above.

    ### Try it out:

      tts --model_name vocoder_models--en--ljspeech--univnet --text "hello, how are you today?"

Files

coqui-ai/TTS-v0.2.0.zip

Files (14.8 MB)

Name Size Download all
md5:a1670ee87b3b38fbe9df6b780fc3b4d8
14.8 MB Preview Download

Additional details

Related works

Is supplement to
https://github.com/coqui-ai/TTS/tree/v0.2.0 (URL)