v0.7.1

版本发布时间: 2023-07-24 17:20:02

SYSTRAN/faster-whisper最新发布版本:v1.0.3(2024-07-01 18:05:08)

Fix a bug related to no_speech_threshold: when the threshold was met for a segment, the next 30-second window reused the same encoder output and was also considered as non speech
Improve selection of the final result when all temperature fallbacks failed by returning the result with the best log probability