whisper.cpp

public_git/whisper.cpp

Fork 0

mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-22 03:48:19 +02:00

Commit Graph

Author	SHA1	Message	Date
Karthick	f897eb7670	whisper : support no_speech_thold (#2625 ) * Implement no_speech_thold no_speech_thold functionality is on par with OpenAI's whisper * Addressed review comments	2024-12-17 19:15:47 +02:00
KarthickandGeorgi Gerganov	2f2841bfce	whisper : add single-timestamp logic (#2629 ) * Fix hallucinations during silence When the predicted tokens end with a single timestamp the the entire 30 segment should be considered as done, to avoid hallucinations for the remaining part of segment. This behaviour is on par with openai's whisper. Refer to logic related to `single_timestamp_ending` in https://github.com/openai/whisper/blob/main/whisper/transcribe.py * Accept review comments related to formatting. Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>	2024-12-17 19:07:08 +02:00

Author

SHA1

Message

Date

Karthick

f897eb7670

whisper : support no_speech_thold (#2625 )

* Implement no_speech_thold

no_speech_thold functionality is on par with OpenAI's whisper

* Addressed review comments

2024-12-17 19:15:47 +02:00

KarthickandGeorgi Gerganov

2f2841bfce

whisper : add single-timestamp logic (#2629 )

* Fix hallucinations during silence

When the predicted tokens end with a single timestamp the the entire 30 segment should be considered as done, to avoid hallucinations for the remaining part of segment.
This behaviour is on par with openai's whisper. Refer to logic related to `single_timestamp_ending` in https://github.com/openai/whisper/blob/main/whisper/transcribe.py

* Accept review comments related to formatting.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

2024-12-17 19:07:08 +02:00