Vaibhavs10 insanely-fast-whisper issues

Vaibhavs10 / insanely-fast-whisper

Apache License 2.0

6.91k stars 506 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

aten::isin.Tensor_Tensor_out is not currently implemented for the MPS device

#234 Amandrs opened 1 week ago
1
Incompatible with NumPy 2.0...

#233 chadacious opened 1 week ago
3
Updated convert_output.py

#232 DavidScann opened 1 week ago
0
--timestamp word : WhisperFlashAttention2 attention does not support output_attentions

#231 mayunchao1994 opened 2 weeks ago
2
Speaker diarization

#230 wanderGuy opened 3 weeks ago
1
If only convert_output.py did paragraphs (for readibility)

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

#228 WSHAPER opened 1 month ago
0
No VAD?

#227 twicer-is-coder opened 1 month ago
0
"No module named wheel" when adding flash-attn on Windows

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

#225 paulz opened 1 month ago
6
Diarization is very slow

#224 prkumar112451 opened 1 month ago
1
💬 Add BitsAndBytesConfig Optimization Method

#223 kadirnar opened 1 month ago
1
Get nearly double the performance gap with another docker image on the same system.

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

#221 Yasand123 opened 1 month ago
0
Torch not compiled with CUDA enabled

#220 welldawell opened 1 month ago
2
NotImplementedError: The operator 'aten::isin.Tensor_Tensor_out'

#219 cyrilzakka opened 1 month ago
3
{ Feature request} Turn off Progress bar so it can run in batch.

#218 trobinson03195 opened 1 month ago
0
where does insanely-fast-whisper store the downloaded model file?

#217 yinwei168 opened 1 month ago
2
python inference code not different from "normal" whipser?

#216 wincing2 opened 2 months ago
0
[Error] metadata-generation failed while trying to install flash-attention on google collab T4

#215 MahdeenSky opened 2 months ago
0
Local file

#214 kamalkech opened 2 months ago
0
pipx install insanely-fast-whisper outdated version

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

#212 SpeederSpeederSpeder opened 2 months ago
0
Cuda Index Out of Bound error on GPU

#211 weichunnn opened 2 months ago
0
Getting `Use model.to('Cuda')` when trying to use Flash Attention

#210 eburgwedel opened 2 months ago
1
question: client sdk

#209 Tyrese-FullStackGenius opened 2 months ago
0
Timestamps are too tight when repetition_penalty is present

#208 Brodski opened 2 months ago
1
Can I add - initial_prompt like whisper

#207 lvjin521 opened 2 months ago
1
MPS flash attention support

#206 dreampuf opened 2 months ago
0
Speaker Diarization

#205 Yonahfireman opened 2 months ago
0
Using with replicate.com

#204 jjones3535a opened 2 months ago
0
remove python 3.12 warning

#203 tmm1 closed 1 month ago
1
The speed is slower than fast-whisper, is something wrong in my config?

#202 Green-li opened 3 months ago
1
Argument to allow CPU usage for diarization (to allow for low memory systems)

#201 jamtholee opened 3 months ago
0
What is the trade off in accuracy from fp32 to fp16

#200 KeystoneScience opened 3 months ago
0
Out Of memory & attempt to get argmin of an empty sequence

#199 learner0333 opened 3 months ago
2
Add API layer, docker image that is cloud deployable

#198 yoeven opened 3 months ago
0
Error for Multiple languages audio

#197 SaddamBInSyed opened 3 months ago
1
question on how this works?

#196 silvacarl2 opened 3 months ago
2
Тема

#195 DaniilBornosuz closed 3 months ago
0
Is there a way to cap the max length of the transcription?

#194 wtlow003 opened 4 months ago
0
[FEATURE REQUEST] support audio input from microphones

#193 RonnyPfannschmidt opened 4 months ago
0
is_flash_attn_2_available() returns False

#192 Majdoddin opened 4 months ago
0
Too high vRAM usage

#191 Majdoddin opened 4 months ago
0
add ffmpeg install instructions

#190 nabati opened 4 months ago
0
api in replicate.com throws Prediction failed. invalid load key, '\x00'. error randomly

#189 bharatMW opened 4 months ago
0
num-speakers not yet available for pipx installed package

#188 skol101 opened 4 months ago
1
I run code in colab and output comes with terms like ''{"speakers": [], "chunks": [{"timestamp": [0.0, 130.4]'' I would like to transcribe only the text - Is this possible ? How?

#187 maria88hds opened 4 months ago
1
How about some honest speed/quality tests for a change

#186 BBC-Esq opened 4 months ago
0
Can insanely-fast-whisper support real-time transcription with websockets?

#185 joaogabrieljunq opened 4 months ago
0