diff options
| author | historia <historiavg@proton.me> | 2026-08-19 02:10:13 -0400 |
|---|---|---|
| committer | historia <historiavg@proton.me> | 2026-08-19 02:10:13 -0400 |
| commit | 11384921323f7b08271be0607d8df774489a1f7d (patch) | |
| tree | 90b78855cce256dea077ed72dd822ae1fbb1696f /README.md | |
| parent | a89daa1af05e2816f970d6a7b28a07df4f102f7d (diff) | |
| download | tts-audiobook-generator-11384921323f7b08271be0607d8df774489a1f7d.tar.gz | |
fix: reduce chunk size to 40
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 4 |
1 files changed, 4 insertions, 0 deletions
@@ -188,6 +188,10 @@ Third-party wheels: https://mjunya.com/flash-attention-prebuild-wheels/ (hosted Transcription affects the output a lot. Whisper is okay, but does not give perfect transcription. A manual transcription passed via `--transcription` is better. +Keep `CHUNK_SIZE_WORDS` small (default 40). Every API call is a single model generation: long generations lose prosody, can degrade into garbled audio, and text past the model's token limit is never spoken. If parts of a book sound flat, monotone, or garbled, the chunk size is the first thing to check. + +`MIN_DELAY_BETWEEN_CHUNKS` only matters for hosted demos (rate limits); a local server needs no delay (default 0). + Manual transcription, imperfect whisper transcription, and `--no-transcription` each provide different results. Usually the most accurate transcription is the best, but sometimes `--no-transcription` can produce a flat tone that might be preferable for certain voices. Even tiny amounts of pause between phrases in the sample audio can have a big impact. Try increasing or decreasing them. |