Vaibhavs10 insanely-fast-whisper issues

Vaibhavs10 / insanely-fast-whisper

Apache License 2.0

7.76k stars 547 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Can I serve speechbrain trained model whisper with faster whisper?

#254 cod3r0k opened 1 week ago
0
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')`.

#253 solarslurpi opened 1 week ago
1
modal local path support

#252 trigsoft opened 2 weeks ago
0
Whisper.cpp support when?

#251 vedku opened 1 month ago
0
Subtitle file for an audio with proper formatting for .srt and Premiere pro?

#250 krigeta closed 3 weeks ago
0
Torch not compiled with CUDA enabled

#249 Ryan147 opened 1 month ago
0
Major Misidentification Issues in Diarization

#248 andonagio opened 1 month ago
6
Prediction failed: attempt to get argmin of an empty sequence

#247 wscourge opened 2 months ago
0
Any way to transcribe entire directory and output as srt/vtt?

#246 snwefly opened 2 months ago
0
flash_attention_2 on macOS?

#245 yukiarimo opened 2 months ago
0
not working on macOS

#244 mrveritas opened 2 months ago
3
How to keep model in high alert state for faster inference?

#243 SuperMaximus1984 opened 2 months ago
1
Can flash attention 2 be installed on Mac m2pro?

#242 dazzng opened 2 months ago
1
Medium model produces nonsense

#241 tjongsma opened 3 months ago
0
Performing speaker diarization without CLI?

#240 sidharthrajaram closed 3 months ago
2
convert_output.py " 'charmap' codec can't decode byte 0x90"

#239 thebigboss9018 opened 3 months ago
0
segmentation and diarization

#238 danielbowne opened 3 months ago
3
NotImplementedError

#237 Eli-117 closed 4 months ago
0
This is how you solve "Torch installed w/out Cuda" error

#236 gjnave opened 4 months ago
4
Insanely Fast Whispher with TensorRT / ONNX

#235 asusdisciple opened 4 months ago
1
aten::isin.Tensor_Tensor_out is not currently implemented for the MPS device

#234 Amandrs opened 5 months ago
1
Incompatible with NumPy 2.0...

#233 chadacious opened 5 months ago
3
Updated convert_output.py

#232 DavidScann opened 5 months ago
0
--timestamp word : WhisperFlashAttention2 attention does not support output_attentions

#231 mayunchao1994 opened 5 months ago
3
Speaker diarization

#230 wanderGuy opened 5 months ago
1
If only convert_output.py did paragraphs (for readibility)

#229 cleesmith opened 5 months ago
1
Question/Feature: Convert Output Text Format using CLI

#228 WSHAPER opened 6 months ago
0
No VAD?

#227 twicer-is-coder opened 6 months ago
0
"No module named wheel" when adding flash-attn on Windows

#226 jenny923432 opened 6 months ago
1
`The operator 'aten::isin.Tensor_Tensor_out' is not currently implemented for the MPS device.` while running on macOS

#225 paulz opened 6 months ago
9
Diarization is very slow

#224 prkumar112451 opened 6 months ago
2
💬 Add BitsAndBytesConfig Optimization Method

#223 kadirnar closed 4 months ago
2
Get nearly double the performance gap with another docker image on the same system.

#222 lordofriver opened 6 months ago
1
[Question] Usage for consumer hardware?

#221 Yasand123 opened 6 months ago
1
Torch not compiled with CUDA enabled

#220 welldawell closed 4 months ago
4
NotImplementedError: The operator 'aten::isin.Tensor_Tensor_out'

#219 cyrilzakka opened 6 months ago
3
{ Feature request} Turn off Progress bar so it can run in batch.

#218 trobinson03195 opened 6 months ago
0
where does insanely-fast-whisper store the downloaded model file?

#217 yinwei168 opened 6 months ago
3
python inference code not different from "normal" whipser?

#216 wincing2 opened 6 months ago
1
[Error] metadata-generation failed while trying to install flash-attention on google collab T4

#215 MahdeenSky opened 7 months ago
0
Local file

#214 kamalkech opened 7 months ago
0
pipx install insanely-fast-whisper outdated version

#213 LaansDole opened 7 months ago
2
Could we talk in discord mp about subtitles

#212 SpeederSpeederSpeder opened 7 months ago
0
Cuda Index Out of Bound error on GPU

#211 weichunnn opened 7 months ago
0
Getting `Use model.to('Cuda')` when trying to use Flash Attention

#210 eburgwedel opened 7 months ago
4
question: client sdk

#209 Tyrese-FullStackGenius opened 7 months ago
0
Timestamps are too tight when repetition_penalty is present

#208 Brodski opened 7 months ago
2
Can I add - initial_prompt like whisper

#207 lvjin521 opened 7 months ago
1
MPS flash attention support

#206 dreampuf opened 7 months ago
0
Speaker Diarization

#205 Yonahfireman opened 7 months ago
0