alihan/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2023-11-04 02:52:44 +03:00
Code Issues Packages Projects Releases Wiki Activity

stream : add "audio_ctx" parameter

Browse Source 
Used to overwrite the audio context size of the Encoder.
For example, setting "audio_ctx = 512" will make it run about 3 times
faster, processing about 10s of audio, instead of 30s.

The transcription quality drops, but this can be used for real-time
streaming purposes where performance is important.
This commit is contained in:
Georgi Gerganov
2022-11-20 21:12:01 +02:00
parent 62b5ff875c
commit fb8d77f760
3 changed files with 24 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
whisper.h
View File

@@ -24,8 +24,6 @@
#define WHISPER_HOP_LENGTH 160
#define WHISPER_CHUNK_SIZE 30
#define WHISPER_EXPERIMENT_AUDIO_CTX 512
#ifdef __cplusplus
extern "C" {
#endif
@@ -207,7 +205,8 @@ extern "C" {
int max_tokens; // max tokens per segment (0 = no limit)
// [EXPERIMENTAL] speed-up techniques
bool speed_up; // speed-up the audio by 2x using Phase Vocoder
bool speed_up; // speed-up the audio by 2x using Phase Vocoder
int audio_ctx; // overwrite the audio context size (0 = use default)
const char * language;