r0.1.1
PaddlePaddle/PaddleSpeechr0.1.1Jan 14, 2022by Jackwaterveg
AI Summary
A minor update focusing on CLI improvements, the addition of four ASR decoding methods, and refinements to TTS models including speaker embedding support.
Key Highlights
- ASR: Added 4 decoding methods (greedy, beam search, attention, rescoring).
- TTS: Added speaker embedding and ID support for FastSpeech2.
- CLI: Added statistics and unit test capabilities.
- Unified configs for ASR and ST tasks.
- TTS: Added Style MelGAN and HiFiGAN vocoders.
New Features
- English ASR support via Transformer Librispeech model
- Support for finetuning SpeedySpeech
- Refactor Punctuation Restoration example
- Update VCTK Parallel WaveGAN and Multi Band MelGAN
- Fix some frontend bugs in TTS
Full Release Notes
# New Features ## CLI : - Add cli stats. #1274 - Add unit test. #1321 - ASR: Support English: Add transformer_libirspeech model. #1297 - ASR: Support 4 decoding methods: ctc_greedy_search, ctc_beam_search, attention, attention_rescoring. #1297 - ASR & ST: Use the unified config. #1305 / #1312 - ASR: Refactor the code. #1260 by **@AdamBear** - TTS: Support long input text by default. #1241 - TTS: Add Style MelGAN and HiFiGAN. #1241 ## ASR - Refactor configs in examples. #1225 ## TTS - Fix some frontend bugs. #1262 by **@JiehangXie** / #1310 - Add speaker embedding and speaker id for style fastspeech2 inference. #1197 by **@jerryuhoo** - Add support for finetuning speedyspeech. #1302 by **@jerryuhoo** / #1322 / #1337 - Update VCTK Parallel WaveGAN. #1294 - Update Multi Band MelGAN. #1272 ## ST - Refactor configs in examples. #1225 ## Text - Refactor Punctuation Restoration example. #1215 ## Docs - Add topic note for releasing python packages - Add TTS papers. #1330 - Add Frontend G2P topic. #1254 ## Others - Update released models and results. #1306 # Acknowledgements @zh794390558 @yt605155624 @Jackwaterveg @KPatr1ck @Mingxue-Xu @JiehangXie @grasswolfs @jerryuhoo @AdamBear @LittleChenCc @JamesLim-sy