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

Add: More clarity of what "max_new_tokens" does (#658)

Browse Source 
* Add: More clarity of what "max_new_tokens" does
This commit is contained in:
Purfview
2024-01-28 20:40:33 +00:00
committed by GitHub
parent 64b9f244bd
commit 3aec421849
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
faster_whisper/transcribe.py
View File

@@ -267,8 +267,8 @@ class WhisperModel:
https://github.com/snakers4/silero-vad. https://github.com/snakers4/silero-vad.
vad_parameters: Dictionary of Silero VAD parameters or VadOptions class (see available vad_parameters: Dictionary of Silero VAD parameters or VadOptions class (see available
parameters and default values in the class `VadOptions`). parameters and default values in the class `VadOptions`).
max_new_tokens: Maximum number of new tokens to generate. If not set, the maximum will be max_new_tokens: Maximum number of new tokens to generate per-chunk. If not set,
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.