Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / SYSTRAN/faster-whisper issues and pull requests

#941 - can't get it to use GPU

Issue - State: open - Opened by M2ATrail 4 months ago - 4 comments

#940 - Revert the batched process updates for the future of the faster-whisper

Pull Request - State: closed - Opened by aligokalppeker 4 months ago - 29 comments

#939 - how to check hallucination?

Issue - State: open - Opened by RichardQin1 4 months ago

#938 - GUI ?

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

#936 - Use Silero VAD in Batched Mode

Pull Request - State: closed - Opened by MahmoudAshraf97 4 months ago - 28 comments

#935 - I can‘t find BatchedInferencePipeline.

Issue - State: closed - Opened by ZHJ19970917 4 months ago - 6 comments

#934 - 1.0.3 VAD v5 is much worse than 1.0.2 VAD v4

Issue - State: open - Opened by zx3777 4 months ago - 15 comments

#932 - IMPORTANT: pyannote of the 1.0.3 source code

Issue - State: closed - Opened by ckgithub2019 4 months ago - 2 comments

#931 - For audio with a sample rate of 16kHz

Issue - State: closed - Opened by joseph16388 4 months ago - 2 comments

#926 - highest precision level on cpu?

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

#925 - vadOptions default value

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

#919 - Segment timestamps are buggy in BatchedInferencePipeline

Issue - State: closed - Opened by kalradivyanshu 4 months ago - 6 comments

#918 - Issues with automatic language detection

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

#917 - major slowdown with batching commit - cpu only

Issue - State: closed - Opened by ooobo 4 months ago - 22 comments

#915 - Need ability to send multiple files in one go

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

#913 - Does Faster-Whisper support float8?

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

#900 - ValueError exception when no language is detected

Issue - State: closed - Opened by dodysw 5 months ago - 4 comments

#898 - Filter out non_speech_tokens in suppressed tokens

Pull Request - State: closed - Opened by jordimas 5 months ago

#879 - How to choose the CUDA 12 version? Can it support CUDA 12.2?

Issue - State: closed - Opened by jacobtang 6 months ago - 2 comments

#856 - New PR for Faster Whisper: Batching Support, Speed Boosts, and Quality Enhancements

Pull Request - State: closed - Opened by Jiltseb 6 months ago - 98 comments

#854 - Finetuning with Dora

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

#851 - Batch process available?

Issue - State: closed - Opened by lionsheep24 6 months ago - 2 comments

#846 - fix: grouping audio frames causes memory problems and is maybe slightly slower?

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

#839 - clip_timestamps does not work across multiple files [faster-whisper 1.0.2]

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

#825 - Gibberish Outputs

Issue - State: closed - Opened by RohitMidha23 7 months ago - 3 comments

#825 - Gibberish Outputs

Issue - State: closed - Opened by RohitMidha23 7 months ago - 3 comments

#824 - Model not producing accurate transcriptions in Python

Issue - State: closed - Opened by arunman1kandan 7 months ago - 13 comments

#822 - How to use the local cached model?

Issue - State: closed - Opened by LXRee 7 months ago - 6 comments

#820 - Transcribe crash jupyter notebook kernels

Issue - State: open - Opened by GiCollini 7 months ago - 8 comments

#815 - Issues with Capitalization and Punctuation in Transcribed Audios

Issue - State: open - Opened by RomanLeo2003 7 months ago - 2 comments

#806 - no kernel image is available for execution on the device

Issue - State: open - Opened by liu1352183717 7 months ago - 13 comments

#806 - no kernel image is available for execution on the device

Issue - State: open - Opened by liu1352183717 7 months ago - 13 comments

#800 - change subtitles lenght per line

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

#788 - question: client sdk

Issue - State: closed - Opened by Tyrese-FullStackGenius 8 months ago - 1 comment

#788 - question: client sdk

Issue - State: closed - Opened by Tyrese-FullStackGenius 8 months ago - 1 comment

#786 - Word-level timestamps are off by some multiplier

Issue - State: closed - Opened by nikans 8 months ago - 2 comments

#786 - Word-level timestamps are off by some multiplier

Issue - State: closed - Opened by nikans 8 months ago - 2 comments

#782 - How to run

Issue - State: closed - Opened by BloumEM 8 months ago - 2 comments

#782 - How to run

Issue - State: closed - Opened by BloumEM 8 months ago - 2 comments

#781 - Problem with audio

Issue - State: closed - Opened by Herzfrequenz21 8 months ago - 5 comments

#778 - I can't use language='zh' when I use large-v3

Issue - State: closed - Opened by wntg 8 months ago - 3 comments

#778 - I can't use language='zh' when I use large-v3

Issue - State: closed - Opened by wntg 8 months ago - 3 comments

#777 - Large-v3 model hallucinates, large-v2 doesn't

Issue - State: closed - Opened by Arche151 8 months ago - 8 comments

#777 - Large-v3 model hallucinates, large-v2 doesn't

Issue - State: closed - Opened by Arche151 8 months ago - 8 comments

#776 - CUDA Initialisation error

Issue - State: open - Opened by RohitMidha23 8 months ago - 4 comments

#764 - Supporting Distil-Whisper

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

#763 - run error

Issue - State: closed - Opened by tuocheng0824 8 months ago - 3 comments

#761 - Change Time format from seconds to hour:minutes:seconds

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

#757 - Super long video processing failure

Issue - State: closed - Opened by another1s 8 months ago - 7 comments

#754 - initial_prompt

Issue - State: closed - Opened by huhuhu5798 8 months ago - 1 comment

#754 - initial_prompt

Issue - State: closed - Opened by huhuhu5798 8 months ago - 1 comment

#753 - silero_vad.onnx failed. File doesn't exist

Issue - State: open - Opened by ghj1976 8 months ago - 1 comment

#752 - Kernel dies when trying to run model.transcribe

Issue - State: open - Opened by everypidigit 8 months ago - 9 comments

#745 - Using GPU blocks for a few seconds after successful recognition

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

#744 - beam_size size not working if using converted model

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

#743 - How to get the vtt file like i do in whisper?

Issue - State: closed - Opened by Abdelrhman-Sayed70 9 months ago - 1 comment

#742 - Random YouTube transcriptions being returned by `large-v3` model

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

#741 - API server compatible with OpenAI

Issue - State: closed - Opened by rvsh2 9 months ago - 2 comments

#733 - Using distil-whisper-large-v3 German Model from HF with faster-whisper?

Issue - State: closed - Opened by Arche151 9 months ago - 8 comments

#731 - Feature/add hotwords

Pull Request - State: closed - Opened by jax-explorer 9 months ago - 19 comments

#726 - End of sequence token problem.

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

#718 - Confused about recently added distil-whisper support (CPU?)

Issue - State: closed - Opened by Arche151 9 months ago - 2 comments

#717 - Library libcublas.so.12 is not found

Issue - State: open - Opened by Xiaomingpapapa 9 months ago - 12 comments

#717 - Library libcublas.so.12 is not found

Issue - State: open - Opened by Xiaomingpapapa 9 months ago - 12 comments

#716 - Transcription is creating duplicate sentences

Issue - State: closed - Opened by greerviau 9 months ago - 9 comments

#712 - Question about Tensor Input Size Changes in Version 1.0.0

Issue - State: closed - Opened by kale4eat 9 months ago - 4 comments

#711 - 1.0 fix yet for faster-whisper?

Issue - State: closed - Opened by BBC-Esq 9 months ago - 13 comments

#704 - PyPI 0.10.0

Issue - State: closed - Opened by Moumeneb1 9 months ago - 2 comments

#703 - slower inference with 1.0.0 compared to 0.10.0

Issue - State: closed - Opened by thomasmol 9 months ago - 2 comments

#701 - Large-v3 model Issues

Issue - State: closed - Opened by wjc1989 9 months ago - 1 comment

#700 - How to implement microphone transcription using Faster Whisper?

Issue - State: closed - Opened by 20246688 9 months ago - 3 comments

#693 - CMD usage

Issue - State: closed - Opened by FurkanGozukara 9 months ago - 5 comments

#691 - No module named 'faster_whisper'

Issue - State: closed - Opened by nirual81 10 months ago - 9 comments

#688 - distil + word_timestamps=True => CRASH

Issue - State: closed - Opened by ExtReMLapin 10 months ago - 4 comments

#688 - distil + word_timestamps=True => CRASH

Issue - State: closed - Opened by ExtReMLapin 10 months ago - 4 comments

#686 - Transcription is working badly without internet connection

Issue - State: closed - Opened by Da6hkin 10 months ago - 2 comments

#682 - Update PyPi package

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

#677 - README.md L70 specifies Python 3.8 or greater

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

#673 - Transcription gap after songs

Issue - State: closed - Opened by EricVee68 10 months ago - 3 comments

#673 - Transcription gap after songs

Issue - State: closed - Opened by EricVee68 10 months ago - 3 comments

#667 - update: Ensure method `_asdict` also converts Word object into a native dict

Pull Request - State: open - Opened by klebster2 10 months ago - 1 comment

#667 - update: Ensure method `_asdict` also converts Word object into a native dict

Pull Request - State: closed - Opened by klebster2 10 months ago - 2 comments