EveryVoiceTTS / EveryVoiceTTS/EveryVoice
Add model configuration validation to anticipate out-of-memory errors
Open
enhancement
- Dominant language
- Python
- Stars
- 45
- Forks
- 4
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 14
Description
something that checks that this number isn’t too big: `n_mels * 1/(fft_hop_frames / input_sampling_rate)` maybe also in relation to `max_audio_length`
Contributor guide
Assessment
This issue has not been assessed yet.