You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
|
1 year ago | |
---|---|---|
.. | ||
TTSAndroid | 1 year ago | |
TTSArmLinux | 1 year ago | |
TTSCppFrontend | 1 year ago | |
asr_deployment | 2 years ago | |
audio_content_search | 2 years ago | |
audio_searching | 2 years ago | |
audio_tagging | 2 years ago | |
automatic_video_subtitiles | 2 years ago | |
custom_streaming_asr | 2 years ago | |
keyword_spotting | 2 years ago | |
metaverse | 2 years ago | |
punctuation_restoration | 2 years ago | |
speaker_verification | 2 years ago | |
speech_recognition | 2 years ago | |
speech_server | 2 years ago | |
speech_ssl | 2 years ago | |
speech_translation | 2 years ago | |
speech_web | 2 years ago | |
story_talker | 2 years ago | |
streaming_asr_server | 2 years ago | |
streaming_tts_server | 2 years ago | |
streaming_tts_serving_fastdeploy | 2 years ago | |
style_fs2 | 2 years ago | |
text_to_speech | 1 year ago | |
whisper | 2 years ago | |
README.md | 2 years ago | |
README_cn.md | 2 years ago |
README.md
Speech Application based on PaddleSpeech
(简体中文|English)
This directory contains many speech applications in multiple scenarios.
- audio searching - mass audio similarity retrieval
- audio tagging - multi-label tagging of an audio file
- automatic_video_subtitles - generate subtitles from a video
- metaverse - 2D AR with TTS
- punctuation_restoration - restore punctuation from raw text
- speech recognition - recognize text of an audio file
- speech server - Server for Speech Task, e.g. ASR,TTS,CLS
- streaming asr server - receive audio stream from websocket, and recognize to transcript.
- streaming tts server - receive text from http or websocket, and streaming audio data stream.
- speech translation - end to end speech translation
- story talker - book reader based on OCR and TTS
- style_fs2 - multi style control for FastSpeech2 model
- text_to_speech - convert text into speech
- self supervised pretraining - speech feature extraction and speech recognition based on wav2vec2
- Wishper - speech recognize and translate based on Whisper model