Features

CLI : New Feature

• Easy install by pip pip install paddlespeech
• CLI to quick explore ASR, TTS, audio classification, speech translation and punctuation restoration.

ASR

• Join CTC LM decoder
  • paper link
• Transformer LM model
• Improve DeepSpeech2 online model
• Refactor some configs

TTS

• Merge Parakeet into PaddleSpeech
• Add FastSpeech2-Conformer
  • paper link: fastspeech2 、conformer
  • example link
• Add Multi Band MelGAN
  • paper link
  • example link
• Add HiFiGAN
  • paper link
  • example link
• Add Style MelGAN
  • paper link
  • example link
• Add FastSpeech2 Voice Cloning with GE2E (SV2TTS)
  • paper link
  • example link

CLS

• Add audio classification example on ESC-50 and custom dataset.
• Add audio tagging demo based on PANNs and Audioset labels.

ST

• ST-MTL
• FAT-ST-MTL

Docs

• Add quick start
• Add read the doc
• Improve installation documentation
• Add README for each example

Demos

• Audio_tagging
• Automatic_video_subtitiles
• Metaverse
• Punctuation_restoration
• Speech_recognition
• Speech_translation
• Story_talker
• Style_fs2
• Text_to_speech

Others

• Update released models and results

Acknowledgements

@zh794390558 @KPatr1ck @Jackwaterveg @yt605155624 @Mingxue-Xu @grasswolfs @jerryuhoo

1. ctc alignment
2. refactor data pipeline
3. autolog for deepspeech test
4. refactor checkpoint save/load
5. deepspeech online model
6. mfa alignment example
7. add text normaliztion example
8. TLG for aishell
9. more dataest: thchs30, aidatatang, timit etc.
10. 8k speech example
11. ted en-zh st example
12. more utils

1. Transformer/Conformer Offline/Online ASR
2. Unified CTC Loss for DS2 model and Transformer Model

paddle 1.8.x with python2

master latest code