Vaibhavs10 insanely-fast-whisper issues

Vaibhavs10 / insanely-fast-whisper

Apache License 2.0

6.92k stars 505 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Use as python lib and release format.

#184 jzju opened 4 months ago
1
Doesn't detect CUDA

#183 dgoryeo opened 4 months ago
3
Missing 0.0.13 on pipx?

#182 jacksteamdev closed 4 months ago
1
Normalize CLI Argument Format for Consistency

#181 felixcarmona closed 3 months ago
2
Add Support and Enforce Constraints on Speaker Count Parameters

#180 felixcarmona closed 4 months ago
1
Add VTT and TXT formats to output converter

#179 mjgiarlo closed 4 months ago
1
torch_dtype only for torch.float16？

#178 yumianhuli1 opened 4 months ago
0
FFMPEG is installed but it gives error showing its not.

#177 Brob3r closed 5 months ago
1
Add Script to Convert output.json to .srt Format

#176 Orion-Zheng closed 4 months ago
0
Random and inconsistent transcribe

#175 Auth0rM0rgan closed 4 months ago
4
CLI Feature requests: 1) Output .srt files, 2) Sequentially process all audio files in directory

#174 ch826 opened 5 months ago
1
언어를 변경 할 수 있나요?

#173 souk0721 closed 5 months ago
1
pipx install fails on Mac OS Sonoma

#172 boxabirds opened 5 months ago
3
Word Timestamps

#171 Matheusadler closed 5 months ago
1
Fixes bad version of insanely-fast-whisper being installed on python 3.11.X

#170 zackees closed 5 months ago
1
Updated type in FAQs for `--device-id mps`

#169 paulmeller closed 5 months ago
0
Is there an api to get the transcription progress？

#168 yumianhuli1 opened 5 months ago
0
How is the accuracy and memory usage as compared to Faster Whisper?

#167 bakermanbrian opened 5 months ago
3
Make it possible to install on Python 3.11.4 and later

#166 sergray closed 5 months ago
3
Issue on macOS Ventura - ProductVersion: 13.6.3 - BuildVersion: 22G436?

#165 yvervoort opened 5 months ago
2
In the benchmark table, what does the 'batching [24]' refer to?

#164 SoundingSilence opened 5 months ago
1
Get !!!!! in output.json file

#163 kamil6x opened 5 months ago
0
Cuda Out of Memory

#162 hatimkh20 opened 5 months ago
6
How to make model use 2 GPU?

#161 hatimkh20 opened 5 months ago
0
Remove the model from VRAM

#160 yumianhuli1 opened 5 months ago
0
Make timestamp more accurate

#159 yumianhuli1 closed 5 months ago
0
About "condition_on_previous_text"

#158 yumianhuli1 closed 5 months ago
2
Update README.

#157 Vaibhavs10 closed 5 months ago
0
Way to generate output scores from the pipeline?

#156 sujitv19196 closed 5 months ago
1
Missing option to provide a prompt argument

#155 hlevring closed 5 months ago
1
Add base64 inline audio

#154 kshmir opened 6 months ago
2
Trying to run insanely fast whisper on CPU -

#153 Maldoror1900 closed 5 months ago
2
Change pyannote settings using Insanely-Fast-Whisper?

#152 Maldoror1900 opened 6 months ago
4
ValueError: Transformers now supports natively BetterTransformer optimizations (torch.nn.functional.scaled_dot_product_attention) for the model type whisper. Please upgrade to transformers>=4.36 and torch>=2.1.1 to use it

#151 MiningIrving closed 5 months ago
8
Add CPU device-id support

#150 Tradunsky opened 6 months ago
2
Does this project support other models of whisper base tiny

#149 MiningIrving closed 5 months ago
3
I wonder how many work did this project do?

#148 dyyzhmm closed 5 months ago
1
timestamps are not as accurate as other Whisper implementations

#147 ronyfadel opened 6 months ago
2
Error in Notebook: infer_faster_whisper_large_v2.ipynb

#146 riffov closed 5 months ago
1
Keep getting an error that torch is not compiled with CUDA, why?

#145 hawkeyecz closed 6 months ago
1
added workaround to readme in case pipx cant parse the python version

#144 rklasen closed 6 months ago
0
Can't install versions > 0.0.8 due to wrong python version even when Python 3.11.6 is installed

#143 rklasen closed 6 months ago
2
Ascii codec cant decode byte

#142 asusdisciple closed 6 months ago
1
You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')

#141 asusdisciple closed 6 months ago
1
Cuda out of Memory Error

#140 omarsiddiqi224 closed 6 months ago
4
Better Diarization pipeline

#139 omarsiddiqi224 opened 6 months ago
6
Timestamp is not precise enough.

#138 genicsoft closed 6 months ago
1
Updated to newer usage of flash attn 2, getting rid of warning message

#137 oliverwehrens closed 6 months ago
0
Update non-cli code snippet

#136 sanchit-gandhi closed 6 months ago
0
pipx install failed on BetterTransformer

#135 Utopiah closed 6 months ago
6

Previous Next