[Bugfix] Changed speech to text chunk timestamp to cumulative approach (#41131)

Signed-off-by: Toby Bell <toby.bell1702@hotmail.co.uk>
This commit is contained in:
TobyJBell
2026-07-27 17:06:46 +00:00
committed by GitHub
parent e3c2fc3b3c
commit 15d65f8669
5 changed files with 101 additions and 11 deletions
+1 -1
View File
@@ -195,7 +195,7 @@ Provide a fast duration→token estimate to improve streaming usage statistics:
The API server takes care of basic audio I/O and optional chunking before building prompts:
- Resampling: Input audio is resampled to `SpeechToTextConfig.sample_rate` using `AudioResampler`.
- Chunking: If `SpeechToTextConfig.allow_audio_chunking` is True and the duration exceeds `max_audio_clip_s`, the server splits the audio into overlapping chunks and generates a prompt per chunk. Overlap is controlled by `overlap_chunk_second`.
- Chunking: If `SpeechToTextConfig.allow_audio_chunking` is True and the duration exceeds `max_audio_clip_s`, the server splits the audio into chunks and generates a prompt per chunk. There is no overlap between chunks, overlap_chunk_second controls the size of the search window used to find the split point.
- Energy-aware splitting: When `min_energy_split_window_size` is set, the server finds low-energy regions to minimize cutting within words.
Relevant server logic: