heimoshuiyu/faster-whisper
1
0
Fork 0
Code Issues Pull Requests 1 Packages Projects Releases Wiki Activity

Clarify documentation for hotwords (#817)

Browse Source 
* Clarify documentation for hotwords

* Remove redundant type specifications
This commit is contained in:
Keating Reid
2024-05-05 21:52:59 -04:00
committed by GitHub
parent 8d5e6d56d9
commit 49a80eb8a8
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
faster_whisper/transcribe.py
View File

@@ -294,15 +294,15 @@ class WhisperModel:
the maximum will be set by the default max_length. the maximum will be set by the default max_length.
chunk_length: The length of audio segments. If it is not None, it will overwrite the chunk_length: The length of audio segments. If it is not None, it will overwrite the
default chunk_length of the FeatureExtractor. default chunk_length of the FeatureExtractor.
clip_timestamps: Union[str, List[float]] clip_timestamps:
Comma-separated list start,end,start,end,... timestamps (in seconds) of clips to Comma-separated list start,end,start,end,... timestamps (in seconds) of clips to
process. The last end timestamp defaults to the end of the file. process. The last end timestamp defaults to the end of the file.
vad_filter will be ignored if clip_timestamps is used. vad_filter will be ignored if clip_timestamps is used.
hallucination_silence_threshold: Optional[float] hallucination_silence_threshold:
When word_timestamps is True, skip silent periods longer than this threshold When word_timestamps is True, skip silent periods longer than this threshold
(in seconds) when a possible hallucination is detected (in seconds) when a possible hallucination is detected
hotwords:Optional text hotwords:
add hotwords if set prefix it invalid Hotwords/hint phrases to provide the model with. Has no effect if prefix is not None.
language_detection_threshold: If the maximum probability of the language tokens is higher language_detection_threshold: If the maximum probability of the language tokens is higher
than this value, the language is detected. than this value, the language is detected.
language_detection_segments: Number of segments to consider for the language detection. language_detection_segments: Number of segments to consider for the language detection.