b6bf906730
ref #10 : quick-and-dirty attempt for real-time audio transciption
...
- Processes input in chunks of 3 seconds.
- Padding audio with silence
- Uses 1 second audio from previous pass
- No text context
2 years ago
77d929f603
Fix bug in FFT
...
The FFT routine does not work for odd N
Solution is to add DFT and use it when N is odd
2 years ago
6d654d192a
Fix reading of stereo WAV files
2 years ago
62897e8ae6
Update README.md
2 years ago
15b49e8baf
Bug fix
...
Longer prompts could cause out-of-bounds access
2 years ago
3bcdbdfc32
Reduce memory usage even more + better sampling
...
- The encode/decode memory buffers are now reused
- If the 30-sec segment goes for too long without a timestamp token, we
force one. Improves transcription for large model
- Stereo support
- Add "micro-machines.wav" sample
2 years ago
310f4883d1
Update README.md
2 years ago
fd3f3d748f
Update README.md
2 years ago
5877c3578e
ref #4 : added transcription timestamps
...
Can be turned off with "-nt" argument.
Performance has also improved.
2 years ago
8d4041c31f
Merge pull request #3 from cdosoftei/master
...
Pass -pthread to linker
2 years ago
d4fcfa47b0
Pass -pthread to linker
2 years ago
4352a6018b
Update README.md
2 years ago
f888c2373d
Flash + language support (ref #2 )
...
- Achieved big performance improvement + memory usage reduction
- Can now translate / transcribe different languages
2 years ago
154fa796dd
ref #1 : add -pthread to compilation flags
2 years ago
476182e439
Update README.md and simplify usage
2 years ago
f2456f8d93
Create README.md
2 years ago
28802c4dae
Create LICENSE
2 years ago
b0a11594ae
Initial release
2 years ago
Georgi Gerganov