Softcatala/whisper-ctranslate2 issues and pull requests

#100 - Last master any query exception in cli and web api mode

Issue - State: closed - Opened by slavonnet 25 days ago - 3 comments

#99 - The Timeline of the command line is different from the Timeline of the output file?

Issue - State: open - Opened by zx3777 about 1 month ago - 2 comments

#98 - Getting AttributeError When I try to Run

Issue - State: open - Opened by FriedGenera about 1 month ago

#97 - includes language language as part of the output path extension

Issue - State: open - Opened by drzraf about 1 month ago

#96 - fail safe if no audio available

Issue - State: closed - Opened by drzraf about 1 month ago - 3 comments

#95 - Unable to work with cuda

Issue - State: closed - Opened by fybd88 about 1 month ago - 4 comments

#94 - Python usage

Issue - State: closed - Opened by Hestinorwu about 2 months ago - 1 comment

#93 - Output language code in Json file

Pull Request - State: closed - Opened by lutangar about 2 months ago - 1 comment

#92 - Path to local model directory should be considered a valid model option

Issue - State: closed - Opened by lutangar 2 months ago - 2 comments

#91 - Crash after dedecting language

Issue - State: closed - Opened by kamiMadara 2 months ago - 1 comment

#90 - parallel_for failed: cudaErrorNoKernelImageForDevice on Windows 11 in Powershell

Issue - State: closed - Opened by JeroenSteen 3 months ago

#89 - Disable output_dir?

Issue - State: closed - Opened by otonoton 3 months ago - 1 comment

#88 - Support distil-large-v3

Pull Request - State: closed - Opened by FlippFuzz 3 months ago - 1 comment

#87 - --word_timestamps = True not working

Issue - State: closed - Opened by ollisulopuisto 3 months ago - 1 comment

#86 - Mic input for live transcription

Issue - State: open - Opened by joshoreefe 3 months ago - 3 comments

#85 - Catch an error when user did not accept EULA for pyannote/speaker-dia…

Pull Request - State: closed - Opened by mmokrejs 3 months ago - 1 comment

#84 - Problem running it on Windows 11

Issue - State: closed - Opened by ochiana 4 months ago - 2 comments

#83 - Problem with GPU allocation after updating to CTranslate2 4.0.0

Issue - State: closed - Opened by carolinaxxxxx 4 months ago - 2 comments

#82 - Can you please add support for word_timestamps, highlight_words and max_words_per_line?

Issue - State: closed - Opened by FurkanGozukara 4 months ago - 2 comments

#81 - Exploit found in Malwarebytes

Issue - State: closed - Opened by krstrid 5 months ago

#80 - do not support distil-***.en model

Issue - State: closed - Opened by joostshao 5 months ago - 1 comment

#79 - Save/record the audio into files

Issue - State: closed - Opened by aindilis 5 months ago - 1 comment

#78 - More natural line-wrapping when using --max_line_width

Pull Request - State: open - Opened by JonasCz 6 months ago - 6 comments

#77 - Transcribing from live video stream source

Issue - State: closed - Opened by MyraBaba 6 months ago

#76 - error while installing on windows

Issue - State: closed - Opened by fouda4ever 6 months ago - 1 comment

#75 - Docker image for running whisper-ctranslate2

Issue - State: open - Opened by extremelyonline 7 months ago - 1 comment

#74 - RuntimeError

Issue - State: closed - Opened by Morv55555 7 months ago - 4 comments

#73 - GPU or CoreML acceleration on Mac Arm

Issue - State: closed - Opened by bakaburg1 7 months ago

#72 - Issue with output redirection to R console using processx

Issue - State: closed - Opened by bakaburg1 7 months ago - 2 comments

#71 - Multi Files

Issue - State: closed - Opened by Bazza195 7 months ago - 1 comment

#70 - invalid int value

Issue - State: closed - Opened by trackpot 7 months ago - 1 comment

#69 - stdin support

Pull Request - State: open - Opened by cianyyz 7 months ago - 1 comment

#68 - distill-whisper?

Issue - State: closed - Opened by silvacarl2 8 months ago - 4 comments

#67 - Support Whisper large-v3?

Issue - State: closed - Opened by gary109 8 months ago - 6 comments

#66 - Rust profi/improve microphone detection 2

Pull Request - State: closed - Opened by RustProfi 8 months ago

#65 - detect language

Issue - State: closed - Opened by sicora-pixel 8 months ago - 1 comment

#64 - Running on Macos?

Issue - State: open - Opened by dazzng 8 months ago - 20 comments

#63 - improve microphone detection

Pull Request - State: open - Opened by RustProfi 8 months ago - 3 comments

#62 - Measure times

Issue - State: closed - Opened by sicora-pixel 9 months ago - 1 comment

#61 - Feature request, does use of compute USB stick can accelerate inference?

Issue - State: closed - Opened by mpuz 9 months ago - 1 comment

#60 - Ablility to specify model directory

Issue - State: closed - Opened by BBC-Esq 9 months ago - 1 comment

#59 - Additional quants please!

Issue - State: closed - Opened by BBC-Esq 9 months ago - 7 comments

#58 - unexpected keyword argument 'repetition_penalty

Issue - State: closed - Opened by noisyscott 9 months ago - 3 comments

#57 - Minor Update to whisper_ctranslate2.py - Print file name when verbose

Pull Request - State: closed - Opened by SamuelWN 10 months ago - 1 comment

#56 - 0.2.9 --help explained incorrectly

Issue - State: closed - Opened by zx3777 10 months ago - 1 comment

#55 - How to calculate the probability value of a word?

Issue - State: closed - Opened by TNBT12g 11 months ago - 1 comment

#54 - How to transcibe as fast as possible in a CPU only server?

Issue - State: closed - Opened by tonyho 11 months ago - 2 comments

#53 - 2 hour video but generated transcription of only 35 mins.

Issue - State: closed - Opened by deadcoder0904 12 months ago - 7 comments

#52 - Use the output of --live_transcribe

Issue - State: open - Opened by fatualux 12 months ago - 4 comments

#51 - --live_transcribe does nothing for me in macOS

Issue - State: closed - Opened by adriangalilea 12 months ago - 6 comments

#50 - How to transfer the word-level timestamped json to srt?

Issue - State: closed - Opened by lj739 12 months ago - 4 comments

#49 - can Whisper run on the gaps between each speech section？

Issue - State: closed - Opened by zx3777 about 1 year ago - 1 comment

#48 - argument error when doing vad_filter

Issue - State: closed - Opened by asafarevich about 1 year ago - 1 comment

#47 - initial_prompt?

Issue - State: closed - Opened by silvacarl2 about 1 year ago - 2 comments

#46 - Random stops

Issue - State: closed - Opened by goodenn about 1 year ago - 2 comments

#45 - Help, the software is not working!

Issue - State: closed - Opened by boykan313 about 1 year ago - 10 comments

#44 - Fix windows model loading by restructuring the code

Pull Request - State: closed - Opened by jordimas about 1 year ago - 1 comment

#43 - Is possible to support with ydotool / nerd-dictation in whisper-ctranslate2 ?

Issue - State: closed - Opened by grigio about 1 year ago - 1 comment

#42 - Doesn't accept specified language

Issue - State: closed - Opened by softlypink about 1 year ago

#41 - I get error code 126 with CUDA installed and running.

Issue - State: closed - Opened by francofang about 1 year ago - 4 comments

#40 - Using GPU without any output

Issue - State: closed - Opened by despairTK about 1 year ago - 4 comments

#39 - diarize option?

Issue - State: closed - Opened by thibaultmol about 1 year ago - 2 comments

#38 - Consider adding options list to readme

Issue - State: closed - Opened by thibaultmol about 1 year ago - 2 comments

#37 - It works fine, but gives an error.

Issue - State: closed - Opened by mayjack0312 about 1 year ago

#36 - Please support python API for whisper-ctranslate2

Issue - State: closed - Opened by wjc1989 about 1 year ago - 3 comments

#35 - --verbose argument should work with lowercase true and false

Issue - State: closed - Opened by asolidtime about 1 year ago - 1 comment

#34 - Extending CLI for Fine-Tuned Whisper Models on Hugging Face

Issue - State: closed - Opened by anilbey about 1 year ago - 4 comments

#33 - Live transcription is extremely inaccurate

Issue - State: closed - Opened by coder543 about 1 year ago - 9 comments

#32 - Add select live device

Pull Request - State: closed - Opened by foul11 about 1 year ago - 1 comment

#31 - compress json filesize

Issue - State: closed - Opened by ras0k about 1 year ago - 4 comments

#30 - vad_filter still runs even if 'False' is passed

Issue - State: closed - Opened by mayeaux about 1 year ago - 2 comments

#29 - sometimes srt file not generated

Issue - State: closed - Opened by iorilu about 1 year ago - 11 comments

#28 - How to turn off --highlight_words ?

Issue - State: closed - Opened by zx3777 about 1 year ago - 5 comments

#27 - Please make sure libcudnn_ops_infer.so.8 is in your library path?

Issue - State: closed - Opened by silvacarl2 about 1 year ago - 7 comments

#26 - only works in cpu mode , but gpu outputs nothing

Issue - State: closed - Opened by yslion about 1 year ago - 10 comments

#25 - Fix documentation of --live_transcribe

Pull Request - State: closed - Opened by fflorent about 1 year ago - 1 comment

#24 - Add support for max_line_length and max_line_count

Issue - State: closed - Opened by mayeaux about 1 year ago - 2 comments

#23 - Documentation for translation functionality?

Issue - State: closed - Opened by rsmith02ct about 1 year ago - 3 comments

#22 - Enable faster_whisper debug logs when verbose flag is set

Pull Request - State: closed - Opened by FlippFuzz about 1 year ago

#21 - Use "official" faster-whisper models

Issue - State: closed - Opened by guillaumekln about 1 year ago - 4 comments

#20 - No file output if output folder/type not selected

Issue - State: closed - Opened by rsmith02ct about 1 year ago - 9 comments

#19 - Enable GPU

Issue - State: closed - Opened by fleeasura123 about 1 year ago - 2 comments

#18 - Live Inference API

Issue - State: closed - Opened by aqibsaeed about 1 year ago - 1 comment

#17 - Is it possible to add a flag to display debug logging?

Issue - State: open - Opened by FlippFuzz about 1 year ago

#16 - OSError: PortAudio library not found when using whisper-ctranslate2-0.1.7

Issue - State: closed - Opened by FlippFuzz about 1 year ago - 4 comments

#15 - Error with Japanese subtitles

Issue - State: closed - Opened by rsmith02ct about 1 year ago - 40 comments

#14 - Enabling VAD results in subtitle timing issue

Issue - State: closed - Opened by old9 about 1 year ago - 3 comments

#13 - Support additional params for `faster-whisper` VAD options

Issue - State: closed - Opened by mayeaux about 1 year ago - 1 comment

#12 - 'whisper-ctranslate2' is not recognized as an internal or external command, operable program or batch file.

Issue - State: closed - Opened by stevevaius2015 about 1 year ago - 1 comment

#11 - No outputs

Issue - State: closed - Opened by avc1657 about 1 year ago - 46 comments

#10 - Output file location

Issue - State: closed - Opened by Zacharie-Jacob about 1 year ago - 4 comments

#9 - .DLL's needed to run on Windows Anaconda command prompt

Issue - State: closed - Opened by turnkit about 1 year ago - 3 comments

#8 - Multi audio input support?

Issue - State: closed - Opened by keimaruO about 1 year ago - 6 comments

#7 - Streaming from microhphone

Issue - State: closed - Opened by mirfan899 about 1 year ago - 4 comments

#6 - --model_directory just got broken

Issue - State: closed - Opened by anneriekeschipperen893 about 1 year ago - 6 comments

GitHub / Softcatala/whisper-ctranslate2 issues and pull requests