Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
JackZ2024 opened an issue on SWivid/F5-TTS
The audio synthesized by the model I trained myself has no sound
I have a Thai dataset of more than 5 hours, and I trained 160k. The audio inferred by the model has no sound. What could be the reason?
kmn1024 created a comment on an issue on SWivid/F5-TTS
Just a theory... having this case: https://github.com/SWivid/F5-TTS/blob/main/model/dataset.py#L51 means that get_frame_len (https://github.com/SWivid/F5-TTS/blob/main/model/dataset.py#L32) doesn...
