SYSTRAN/faster-whisper issues and pull requests

#1075 - C++ version for faster_whisper

Issue - State: closed - Opened by BaffledCoder about 1 month ago - 2 comments

#1075 - C++ version for faster_whisper

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

#1074 - Too slow

Issue - State: open - Opened by YasinSharifbeigy about 1 month ago - 4 comments

#1074 - Too slow

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

#1073 - Bad performance

Issue - State: open - Opened by 1848 about 1 month ago - 1 comment

#1073 - Bad performance

Issue - State: closed - Opened by 1848 about 1 month ago - 1 comment

#1071 - Start language detection from a certain time in Batch transcription

Issue - State: closed - Opened by misters2008 about 1 month ago - 1 comment

#1069 - Jimmy dev

Pull Request - State: closed - Opened by jimmy1984xu about 2 months ago

#1068 - Update upstream fork changes

Pull Request - State: closed - Opened by zazpie about 2 months ago

#1067 - Implement suppress_numerals

Pull Request - State: closed - Opened by darkmirage about 2 months ago

#1066 - Revert to origin

Pull Request - State: closed - Opened by mesnilgr about 2 months ago

#1065 - Changes for pypi release

Pull Request - State: closed - Opened by Jiltseb about 2 months ago

#1064 - Gh action

Pull Request - State: closed - Opened by HRashidi about 2 months ago

#1062 - ETA of 1.0.4? Batched inference for pip package

Issue - State: closed - Opened by phu54321 about 2 months ago - 1 comment

#1061 - Cannot Point FasterWhisper to use specific GPU on multi GPU systems

Issue - State: closed - Opened by Seriously-Nonya-Bidness about 2 months ago - 1 comment

#1060 - Empty audio causes failure

Issue - State: closed - Opened by tamis-laan about 2 months ago - 5 comments

#1056 - Add language_detection_only parameter

Pull Request - State: closed - Opened by Frenzie about 2 months ago - 2 comments

#1055 - Memory leak with parallel transcribe

Issue - State: open - Opened by saddy001 about 2 months ago - 1 comment

#1054 - New PR: Allow users to add their own customised model without editing existing faster-whisper code

Pull Request - State: closed - Opened by blackpolarz about 2 months ago - 9 comments

#1053 - Adding the num of segments into TranscriptionInfo

Pull Request - State: closed - Opened by stsfaroz about 2 months ago - 3 comments

#1052 - Adding Segment count to the info

Pull Request - State: closed - Opened by stsfaroz about 2 months ago

#1044 - Language info per segment ?

Issue - State: open - Opened by Matriv-org about 2 months ago - 1 comment

#1039 - Update vad.py

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

#1038 - Update feature_extractor.py

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

#1037 - Utils.py mods to small improvements

Pull Request - State: closed - Opened by BBC-Esq about 2 months ago

#1036 - fix a typo in detect_language_multi_segment comment

Pull Request - State: closed - Opened by fcakyon about 2 months ago - 3 comments

#1034 - Add Open-dubbing into community projects

Pull Request - State: open - Opened by jordimas about 2 months ago

#1031 - BatchedInferencePipeline missing in PyPi release

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

#1030 - Benchmark faster whisper turbo v3

Issue - State: open - Opened by asr-lord 2 months ago - 29 comments

#1029 - draft

Issue - State: closed - Opened by djpg 2 months ago

#1028 - faster whisper turbo v3 got no_speech_prob==0.0

Issue - State: open - Opened by linyubupa 2 months ago - 1 comment

#1027 - Different output of faster-whisper vs whisper-standalone with faster-whisper

Issue - State: closed - Opened by tjongsma 2 months ago - 10 comments

#1025 - Turbo-V3

Issue - State: closed - Opened by freddierice 2 months ago - 27 comments

#1023 - log_progress option

Issue - State: closed - Opened by ROBERT-MCDOWELL 2 months ago - 2 comments

#1022 - RuntimeError: No position encodings are defined for positions >= 448, but got position 448

Issue - State: closed - Opened by RichardQin1 2 months ago - 2 comments

#1021 - audio_split example

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

#1020 - Does this project not support Jetson deployment yet

Issue - State: closed - Opened by litao-zhx 2 months ago - 2 comments

#1018 - Using a partitioned A100 GPU via MIG with device_index?

Issue - State: open - Opened by johnrisby 2 months ago

#1017 - Could not load library libcublasLt.so.11.

Issue - State: open - Opened by nguyenhoanganh2002 2 months ago - 1 comment

#1016 - Cache path?

Issue - State: closed - Opened by ROBERT-MCDOWELL 2 months ago

#1014 - Update transcribe.py

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

#1012 - Could not locate cublasLt64_11.dll

Issue - State: open - Opened by TechInterMezzo 3 months ago

#1011 - [bug] distil-small conversion results in junk!

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

#1009 - Modify the description of "cpu_threads"

Pull Request - State: closed - Opened by Hellwz 3 months ago

#1008 - Issues with pip package (missing attribute detect_language_multi_segment)

Issue - State: closed - Opened by treya-lin 3 months ago - 2 comments

#1006 - FYI: FUTO did an ACFT finetune of whisper that works with <30s of audio

Issue - State: open - Opened by thiswillbeyourgithub 3 months ago

#1002 - Deleted

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

#1000 - Ctranslate2-Converter

Pull Request - State: closed - Opened by BBC-Esq 3 months ago

#999 - Deploy faster-whisper as a native web-app.

Issue - State: open - Opened by animikhaich 3 months ago - 2 comments

#998 - Is docker image `nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04` more suitable than `nvidia/cuda:12.0.0-runtime-ubuntu22.04` for faster-whisper's cudnn requirements?

Issue - State: closed - Opened by yasu-kondo 3 months ago - 3 comments

#997 - Bug - "No active speech found in audio results"

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

#995 - An amazing bug that importing fast whisper conflicts with git

Issue - State: open - Opened by WelkinYang 3 months ago

#994 - CUDA failed with error an illegal memory access was encountered

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

#993 - Fair Benchmarking of Faster-Whisper - Parameter equivalents to Hugginface

Issue - State: open - Opened by asusdisciple 3 months ago - 2 comments

#992 - Memory on GPU not cleared after transcription

Issue - State: open - Opened by DinnoKoluh 3 months ago - 4 comments

#991 - Cyrillic letters in Polish transcription

Issue - State: open - Opened by Venzon 3 months ago

#990 - a simple web-ui for whisper

Issue - State: open - Opened by pika-online 3 months ago

#989 - Duplicate sentences and missing sentences in large-v3

Issue - State: open - Opened by tuocheng0824 3 months ago

#988 - faster-whisper vs whisper: PyAV stops during decode, ffmpeg continues

Issue - State: open - Opened by rodrigofvale 3 months ago - 2 comments

#987 - [Hallucinations] Repetition of words or chunks with own fine-tuned model

Issue - State: open - Opened by asr-lord 3 months ago - 2 comments

#986 - Choice of model output langauge of easiset way to do that?

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

#985 - Very bigger segment (chunk) size (almost 30 second each) with BatchedInferencePipeline

Issue - State: closed - Opened by alamnasim 3 months ago - 4 comments

#984 - Possible to abort transcription?

Issue - State: open - Opened by mariano54 3 months ago - 1 comment

#983 - CUDA initialization error for faster whisper in subprocess

Issue - State: open - Opened by FengJi2021 3 months ago

#982 - Complained that 'Unable to open file model.bin in model' when loading a model folder with 'model.safetensors'

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

#980 - fix:The timestamps for the second and subsequent segments are incorrect

Pull Request - State: closed - Opened by caiwuu 3 months ago

#979 - fix:The timestamps for the second and subsequent segments are incorrect

Pull Request - State: closed - Opened by caiwuu 3 months ago

#977 - Medium model output is nonsense for batched pipeline (for short 15s audio clips)

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

#976 - Are there any plans to publish the latest code to pypi？

Issue - State: closed - Opened by wildwind0 3 months ago - 2 comments

#975 - different transcribe results with same whisper model and same audios in same process

Issue - State: closed - Opened by JH90iOS 3 months ago

#974 - Updated benchmarks please!

Issue - State: open - Opened by BBC-Esq 3 months ago - 11 comments

#973 - Return empty generator when no active speech in transcribe

Pull Request - State: closed - Opened by kenho211 3 months ago - 2 comments

#972 - Return empty generator when no active speech in transcribe

Pull Request - State: closed - Opened by kenho211 3 months ago

#971 - how to use on cudnn9.1.0

Issue - State: closed - Opened by Garyguhaifeng 3 months ago - 2 comments

#970 - Could you provide the source of models before conversion

Issue - State: open - Opened by weitianhan 3 months ago - 1 comment

#969 - Update README.md to include Whisper-WebUI

Pull Request - State: open - Opened by jhj0517 3 months ago

#968 - Better chunking/loading

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

#967 - Error #15: Initializing libiomp5md.dll, but found libomp140.x86_64.dll already initialized.

Issue - State: open - Opened by SiriusArtLtd 4 months ago - 2 comments

#966 - Update README.md to include Speechlib

Pull Request - State: open - Opened by NavodPeiris 4 months ago

#965 - Set CPU threads according to the machine

Pull Request - State: closed - Opened by ozancaglayan 4 months ago - 7 comments

#964 - Thai language error

Issue - State: open - Opened by lukeewin 4 months ago

#963 - Can I server speechbrain model whisper with fasterwhisper?

Issue - State: open - Opened by cod3r0k 4 months ago

#962 - Is it possible to add lora adapter support and switching between adapters as per request ?

Issue - State: open - Opened by Jeevi10 4 months ago

#961 - revert back to using PyAV instead of torch audio

Pull Request - State: closed - Opened by MahmoudAshraf97 4 months ago - 8 comments

#960 - Why does the transcription speed significantly decrease when the WhisperModel instance is wrapped inside a class attribute?

Issue - State: closed - Opened by wildwind0 4 months ago - 4 comments

#959 - RuntimeError: Unsupported model binary version. This executable supports models with binary version v6 or below, but the model has binary version v1936876918.

Issue - State: closed - Opened by DearTan 4 months ago - 1 comment

#958 - limit pytorch version to cudnn8 for `pip install`

Pull Request - State: closed - Opened by NewUserHa 4 months ago - 7 comments

#957 - how to create the gradio UI with faster-whisper

Issue - State: open - Opened by kustcl 4 months ago - 2 comments

#955 - ValueError: Requested int8 compute type, but the target device or backend do not support efficient int8 computation.

Issue - State: open - Opened by facundobatista 4 months ago - 5 comments

#954 - Poor output quality and speed when using batched inference

Issue - State: closed - Opened by ben256 4 months ago - 2 comments

#952 - Suddenly no start, end or text in generator?

Issue - State: closed - Opened by michaelcuneo 4 months ago - 1 comment

#951 - Cannot start faster-whisper

Issue - State: open - Opened by Denis-Kazakov 4 months ago - 8 comments

#950 - Jupyter Lab crashing with faster-whisper

Issue - State: open - Opened by Denis-Kazakov 4 months ago

#949 - Funny and revealing hallucinations

Issue - State: open - Opened by AgatheBauer 4 months ago - 4 comments

#948 - Error:Maximum decoding length >0 while transcribing

Issue - State: open - Opened by pranavbhat12 4 months ago - 1 comment

#946 - Model Seperate GPU Assignment

Issue - State: open - Opened by ibrahimdevs 4 months ago

#945 - Unable to open file 'model.bin' in model 'models\base'

Issue - State: closed - Opened by cup113 4 months ago - 1 comment

GitHub / SYSTRAN/faster-whisper issues and pull requests