MahmoudAshraf97 / whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

Repository from Github https://github.comMahmoudAshraf97/whisper-diarization

MahmoudAshraf97/whisper-diarization Issues

What to do about misattribution?
Updated 6 months ago1
"Your session crashed for an unknown reason" on Google Colab.
Updated 6 months ago4
Resulting .srt file loses synch with audio file used for transcription (Google Colab notebook)
Updated 6 months ago15
Long audio (4 hrs) devours RAM leading to crash
Updated 6 months ago20
Mac M1 (ARM64)
Updated 7 months ago
Small issue in diarize_parallel.py line 166
Updated 7 months ago1
Invalid handle. Cannot load symbol cublasLtCreate
Updated 7 months ago
RuntimeError: cuDNN error: CUDNN_STATUS_SUBLIBRARY_VERSION_MISMATCH on WSL2 Ubuntu24.04
Updated 7 months ago10
Right ASR Wrong Speaker diarization
Updated 7 months ago4
RuntimeError: Unable to open file 'model.bin' in model 'medium.en'
Updated 7 months ago1
FileNotFoundError: [WinError 2]
Updated 7 months ago2
Your session has crashed for an unknown reason
Updated 7 months ago3
Error installing the requirements
Updated 7 months ago1
not dockerfile
Updated 7 months ago
Do Not Recommend Python 3.9
Updated 7 months ago1
Error on launch
Updated 7 months ago4
AssertionError: uroman not found
Closed 7 months ago16
ImportError: cannot import name 'generate_emissions' from 'ctc_forced_aligner'
Updated 7 months ago
Can't get Colab Notebook to work (libcudnn_ops_infer.so.8 error)
Closed 7 months ago2
error: subprocess-exited-with-error
Closed 7 months ago
FileNotFoundError: [WinError 2]
Closed 7 months ago2
error: subprocess-exited-with-error
Updated 7 months ago1
If the original audio is stereo with one speaker on the left and the other on the right, is there a way to tell whisper-diarization that?
Updated 8 months ago1
[Feature Request] Set default line length for subtitles (.srt files) in ctc-forced-aligner
Updated 8 months ago
Diarization of larger, longer audio files does not work
Updated 8 months ago3
Embeddings
Updated 8 months ago2
CUDA out of Memory
Closed 8 months ago8
Unable to load any of {libcudnn_ops.so.9.1.0, libcudnn_ops.so.9.1, libcudnn_ops.so.9, libcudnn_ops.so} Invalid handle. Cannot load symbol cudnnCreateTensorDescriptor
Updated 9 months ago14
Issue with preprocess_text
Updated 9 months ago9
Had various issues recently, likely related to packages
Updated 9 months ago7
Is It Possible to Preload the NeMo Diarization Model for Efficiency?
Closed 9 months ago2
FileNotFoundError: [WinError 2]
Updated 9 months ago8
I have a problem！
Updated 9 months ago1
Slow transcription
Updated 9 months ago5
Issue running diarize_parallel only
Closed 9 months ago7
Poor performance on Vietnamese speech data
Closed 10 months ago3
Pointing to local models
Closed 10 months ago6
perl uroman exit status 2
Updated 10 months ago8
session crashes for an unknown reason
Closed a year ago12
AttributeError: module 'faster_whisper' has no attribute 'BatchedInferencePipeline'
Updated 10 months ago2
Google Colab script fails
Closed 10 months ago2
UnicodeEncodeError: 'ascii' codec can't encode character '\u2014' in position 19022: ordinal not in range(128)
Closed a year ago3
When I run whisper-diarization I get a "Kernel Died" in my terminal
Closed a year ago11
NameError: name 'transcribe_batched' is not defined
Closed a year ago
Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory
Closed a year ago13
Getting word-level timestamps
Closed a year ago1
Problem with diarization.
Closed a year ago6
Time taken seems longer
Closed a year ago3
Poor diarization.
Closed a year ago1
Errors Here
Updated a year ago1