Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
SWivid created a comment on an issue on SWivid/F5-TTS
will close this issue, feel free to open if further questions
SWivid closed an issue on SWivid/F5-TTS
中文如何进行更精细的控制，如多音字、连读等
中文的有些句子多音字、断句和连读模型读的还有一些问题，如何进行控制， eg： 各个区县市更以其得天独厚的户外休闲旅游资源吸引着来自海内外的游客 question: 各个区县市未连读，户外休闲旅游资源未连读被拆开读。 还有多音字如何控制，试了也不支持输入拼音，是否未进行这部分训练支持。
SWivid created a comment on an issue on SWivid/F5-TTS
> So it's possible for DynamicBatchSampler to sometimes exceed the frames_threshold. The `self.get_frame_len()` is intended to get duration exactly for a queried index, while `__getitem__` do ca...
SWivid created a comment on an issue on SWivid/F5-TTS
Our reproduced E2 model doesn't train with that scheme. Check E2 paper:  We just use characters, no random...
SWivid created a comment on an issue on SWivid/F5-TTS
Use lower case as we suggested in readme, or you are telling model to read letter by letter Also check if reference audio uploaded correctly, will show waveform if so
HaileyStorm opened an issue on SWivid/F5-TTS
ARPAbet phoneme pronunciation not working.
When I try to generate text with ARPAbet phones in parenthesis like you see in the "Specifying the pronunciation without model re-training" of https://www.microsoft.com/en-us/research/project/e2-tt...
lishu44275 opened an issue on SWivid/F5-TTS
请问为啥读英语有口音啊，没有地道点的发音吗？
我是克隆了一个中文声音，但是读英文的时候，不地道啊，怎么才能读地道的呢？
