akashmjn/tinydiarize
Minimal extension of OpenAI's Whisper adding speaker diarization with special tokens
PythonMIT
Issues
- 12
Please Release Fine-Tuning Scripts
#14 opened by ohmguru - 1
Outdated link
#25 opened by bwuzhang - 1
What is the point here?!
#21 opened by nandxorandor - 0
Regression cases
#24 opened by mrienstra - 4
HF Transformers Weights
#15 opened by sanchit-gandhi - 0
"ValueError: tuple.index(x): x not in tuple" error when running the demo command
#23 opened by Clara-at-Powder - 0
How to train a new model?
#22 opened by shell1986 - 0
For the additional Pyannote cost, use GPU
#20 opened by ExtReMLapin - 3
Not getting the SPEAKER SEGMENTS
#19 opened by prafulkl - 1
- 1
invalid choice: 'small.en-tdrz'
#16 opened by nahuel89p - 2
Fine-Tuning The `whisper-base` Variant
#17 opened by rsomani95 - 1
Can you please add support for faster-whisper?
#13 opened by hoonlight - 2
ggml converted model
#12 opened by jordibruin - 0