search

PaddlePaddle / PaddleSpeech

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
https://paddlespeech.readthedocs.io
Apache License 2.0
10.87k stars 1.82k forks source link

流式TTS如何修改参数：采样率、语速、音量、发音人 #3270

Open Fmaj7 opened 1 year ago

Fmaj7 commented 1 year ago

请问需要修改哪个模块的代码修改这些参数

yaleimeng commented 1 year ago

采样率、速度、音量可以自己去改代码，逐帧改pcm字节流，不过速度只能调慢不能调快，因为它是流式推理的，最快就是1倍速。

linwownil commented 1 year ago

对TTS有调节采样率、速度、音量需求的朋友要用对应的tts server + tts client才能实现(即paddlespeech.server.bin.paddlespeech_server和paddlespeech.server.bin.paddlespeech_client)，普通的python API(即paddlespeech.cli.tts.infer)并没有提供(不信可以搜仓库里的change_speed)。详细使用可以参考server和client的介绍，CLI或者python接口都可以调

gclm commented 1 year ago

@Fmaj7 请问这个问题你解决了吗？如果解决的能分享一下吗?

gclm commented 1 year ago

对TTS有调节采样率、速度、音量需求的朋友要用对应的tts server + tts client才能实现(即paddlespeech.server.bin.paddlespeech_server和paddlespeech.server.bin.paddlespeech_client)，普通的python API(即paddlespeech.cli.tts.infer)并没有提供(不信可以搜仓库里的change_speed)。详细使用可以参考server和client的介绍，CLI或者python接口都可以调

hi，请教一下你这个主要是用于端到端的tts生成，流式不太支持，我看了他们调用的tts_engine 位置都不太一样 image

linwownil commented 1 year ago

@gclm paddleinference/tts_engine和python/tts_engine都提供了postprocess，online 里面的tts_engine就没有了

gclm commented 1 year ago

@gclm paddleinference/tts_engine和python/tts_engine都提供了postprocess，online 里面的tts_engine就没有了

ok，感谢。

stale[bot] commented 10 months ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.