absadiki/pywhispercpp

Unable to load `quantized` models

Closed this issue · 3 comments

I am trying to load whisper tiny quantized version ( ggml-tiny-q5_1.bin)
i trying this using jupyter kernal in visual studio code
But when i try to run
model = Model('./models/quantized/ggml-tiny-q5_1.bin', print_progress=False)
Kernal is dying ( unable to load quantized model ) remaining unquantized models are working file seems to be issue in quantized version

image

Kindly need someone help !!!

@kishorekaruppusamy, I just pushed a new version 1.2.0 to PYPI that supports the latest version of whisper.cpp.
Quantized models should be working now.

Let me know if you still have any issues ?

@kishorekaruppusamy, I just pushed a new version 1.2.0 to PYPI that supports the latest version of whisper.cpp. Quantized models should be working now.

Let me know if you still have any issues ?

lets check ...

@kishorekaruppusamy, I just pushed a new version 1.2.0 to PYPI that supports the latest version of whisper.cpp. Quantized models should be working now.
Let me know if you still have any issues ?

lets check ...

Thanks for the changes !!!, it working now 💥