MahmoudAshraf97/whisper-diarization
Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
Jupyter NotebookBSD-2-Clause
Pinned issues
Issues
- 15
- 2
AttributeError: module 'faster_whisper' has no attribute 'BatchedInferencePipeline'
#265 opened by Petervg1810 - 2
Google Colab script fails
#268 opened by BlohoJo - 0
Embeddings
#267 opened by Brihith - 12
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
#259 opened by IGaganpreetSingh - 4
Issue running diarize_parallel only
#262 opened by corneliusgerico - 3
UnicodeEncodeError: 'ascii' codec can't encode character '\u2014' in position 19022: ordinal not in range(128)
#264 opened by dyfma321 - 11
- 0
NameError: name 'transcribe_batched' is not defined
#263 opened by busetde - 5
session crashes for an unknown reason
#260 opened by federicoalegria - 13
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
#255 opened by roboatLee - 1
Getting word-level timestamps
#258 opened by argenisleon - 6
Problem with diarization.
#257 opened by Reinmor - 14
- 3
Time taken seems longer
#256 opened by deepakitkar - 1
Poor diarization.
#254 opened by Oguret2 - 1
Errors Here
#252 opened by AndrewBeniston - 1
- 11
OutOfMemoryError during diarization -> how to solve ?
#242 opened by cuistax - 1
Will it be possible to use the whisper "turbo" model?
#247 opened by Herzik - 1
Error when diarizing
#248 opened by JokanaanR - 4
The diarization and word assignment to the speakers are different with every run. Can anyone know how to solve this?
#245 opened by IGaganpreetSingh - 2
Drop Your Feature Requests HERE
#239 opened by MahmoudAshraf97 - 3
- 4
filenotfound
#223 opened by roboatLee - 2
- 3
Installation error. Torchpy version conflict
#236 opened by carkteck - 2
Feature Request: Docker compose install
#237 opened by flefevre - 2
Support for Whisper large-v3-turbo model
#238 opened by shivamtawari - 1
Can I Fine-Tune the Diarization Model to Recognize a Specific Individual's Voice?
#232 opened by shivamtawari - 6
Segmentation fault
#222 opened by yulkame - 1
- 4
Language transcription for German not working.
#229 opened by JokanaanR - 2
cannot import name '_sentencepiece' from partially initialized module 'sentencepiece' (most likely due to a circular import)
#218 opened by chengyou0741 - 1
Check if each ground truth RTTMs were present in the provided manifest file. Skipping calculation of Diarization Error Rate error
#217 opened by danieladi98 - 26
FileNotFoundError
#212 opened by kc01-8 - 8
- 2
- 2
problem in unpacking load_alignment_model
#224 opened by 01Ashish - 1
Failed to install on windows
#221 opened by yumianhuli1 - 2
is this project dead?
#220 opened by ralyodio - 2
Additional punctuation support
#208 opened by hayata-yamamoto - 4
ModuleNotFoundError: No module named 'numpy'
#207 opened by levnikolaevich - 1
Requested float16 compute type, tesla p40
#216 opened by danieladi98 - 5
Deployment options
#215 opened by cristobal-larach - 2
- 3
How to tune speaker diarization error?
#210 opened by hayata-yamamoto - 2
- 2
Doesn't it provide Diarization for Korean?
#200 opened by Dhyungsuk - 2
ubuntu pip install issue
#199 opened by Dhyungsuk