Ecosyste.ms: Issues

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

GitHub / guillaumekln/faster-whisper issues and pull requests

#570 - Can it transcribe in real-time?

Issue - State: closed - Opened by Gracetoh 12 months ago - 1 comment

#566 - Force read-mode in `av.open`

Pull Request - State: open - Opened by ClaytonJY about 1 year ago

#565 - Add support for whisper-large-v3

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

#564 - OOM on 8GB GPU

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

#563 - insanely faster whisper repository bold claims?

Issue - State: open - Opened by BBC-Esq about 1 year ago - 4 comments

#562 - WhisperModel

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

#561 - Bugfix/whisper large v3

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

#559 - Add support for large-v3

Pull Request - State: open - Opened by turicas about 1 year ago - 4 comments

#558 - faster_whisper with Batching

Issue - State: open - Opened by souvikqb about 1 year ago - 1 comment

#557 - [feat] update distil-whisper

Pull Request - State: open - Opened by metame-none about 1 year ago

#556 - What are the minimum requirements to run faster whisper locally?

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

#555 - convert whisper large v3 error

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

#554 - Add GUI faster-whisper project README.md

Pull Request - State: open - Opened by Juergen-J-F about 1 year ago

#553 - Implementation with Large-v3 but with Batching

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

#551 - is faster-whisper.cpp possible?

Issue - State: open - Opened by rawwerks about 1 year ago - 3 comments

#550 - long files are leading to memory crashes (on gpu)

Issue - State: closed - Opened by westhecool about 1 year ago - 8 comments

#549 - Whisper large-v3

Pull Request - State: closed - Opened by flyingleafe about 1 year ago - 8 comments

#548 - feat: code for whisper-large-v3

Pull Request - State: open - Opened by stillmatic about 1 year ago - 47 comments

#547 - Working with Whisper-large-v3

Issue - State: open - Opened by UmarRamzan about 1 year ago - 24 comments

#544 - Will it be possible to use the large-v3 model?

Issue - State: open - Opened by IllyaPysarchuk about 1 year ago - 37 comments

#543 - Build Faster Whisper in a docker container issues

Issue - State: open - Opened by bakermanbrian about 1 year ago - 5 comments

#542 - Adding timestamping information

Pull Request - State: open - Opened by Noah-Grimaldi about 1 year ago

#540 - Typo in language specification 'jw'?

Issue - State: open - Opened by DKWoods about 1 year ago - 1 comment

#539 - Is there any way we can get an example how to translate?

Issue - State: open - Opened by BBC-Esq about 1 year ago - 5 comments

#538 - Distill Whisper

Issue - State: open - Opened by SinanAkkoyun about 1 year ago - 1 comment

#537 - Convert pytorch_model.bin to model.pt

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

#536 - Finetune VAD model

Issue - State: open - Opened by AvivSham about 1 year ago - 2 comments

#533 - Support for Distil-Whisper

Issue - State: open - Opened by sanchit-gandhi about 1 year ago - 12 comments

#532 - Large, large-v1, and large-v2 models always crash on Windows

Issue - State: closed - Opened by DKWoods about 1 year ago - 8 comments

#531 - Added whisper speech typing to community integrations

Pull Request - State: open - Opened by spottenn about 1 year ago

#529 - How to integrate faster-whisper into Schibsteds WAAS?

Issue - State: open - Opened by Arche151 about 1 year ago

#527 - Does it work on Macos?

Issue - State: open - Opened by dazzng about 1 year ago - 5 comments

#526 - Inference time on CPU much slower than posted benchmark

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

#525 - Triton Inference Server

Issue - State: open - Opened by tomukmatthews about 1 year ago - 1 comment

#522 - Add colorize to output file and add HTML format result

Issue - State: open - Opened by slavonnet about 1 year ago - 1 comment

#521 - Can it transcribe and get Simplified Chinese rather than traditional Chinese?

Issue - State: open - Opened by bk111 about 1 year ago - 2 comments

#520 - Possible issue with segment timestamps in prompt

Issue - State: open - Opened by funboarder13920 about 1 year ago

#519 - Greedy decoding

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

#518 - Can faster-whisper support TPU?

Issue - State: open - Opened by ILG2021 about 1 year ago - 4 comments

#517 - Can whisper-faster show text before and after translation

Issue - State: open - Opened by Asma-droid about 1 year ago - 1 comment

#516 - Could not load library libcudnn_ops_infer.so.8

Issue - State: open - Opened by Benny739 about 1 year ago - 7 comments

#515 - amd and/or apple metal/mps acceleration

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

#513 - Update info on cuBLAS and cuDNN libs in README.md

Pull Request - State: open - Opened by Purfview about 1 year ago - 1 comment

#512 - Over lapping audio/Cross talk

Issue - State: open - Opened by ksbedi about 1 year ago - 1 comment

#510 - Stop unexpectedly when started as a Windows service

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

#509 - How to set command to remove output timestamps?

Issue - State: open - Opened by tomkuo1124 about 1 year ago - 2 comments

#508 - Update whisper-standalone-win description in README.md

Pull Request - State: open - Opened by Purfview about 1 year ago - 1 comment

#506 - Repetition of words or chunks with high confidence

Issue - State: open - Opened by benjaminramirezg about 1 year ago - 7 comments

#505 - Docker Image

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

#504 - Update README.md

Pull Request - State: open - Opened by STocidlowski about 1 year ago

#499 - Change onnxruntime requirement to gpu version and update VAD to run on gpu

Pull Request - State: open - Opened by thomasmol about 1 year ago - 3 comments

#498 - supported_languages() function Error

Issue - State: open - Opened by CheshireCC about 1 year ago - 1 comment

#495 - Feature request: progress bar

Issue - State: open - Opened by sillasgonzaga about 1 year ago - 1 comment

#494 - Extract attentions from transcribe

Issue - State: open - Opened by mgaido91 about 1 year ago

#493 - Run with onnxruntime-gpu not working for faster_whisper

Issue - State: closed - Opened by guilhermehge about 1 year ago - 23 comments

#490 - I too got 'Segmentation fault: 11' on my Mac

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

#488 - How to find model size of faster-whisper model

Issue - State: open - Opened by kurianbenoy about 1 year ago - 1 comment

#487 - Adding speech_chunks and sampling_rate to TranscriptionInfo Class

Pull Request - State: open - Opened by guilhermehge about 1 year ago - 1 comment

#486 - Clarification On Keeping The Model Loaded

Issue - State: open - Opened by yb-cs about 1 year ago - 1 comment

#485 - without_timestamps=True generates incorrect results

Issue - State: open - Opened by patriotyk about 1 year ago - 3 comments

#483 - transcribe task output translate result

Issue - State: open - Opened by wylqq312715289 about 1 year ago - 3 comments

#482 - I have a problem with the timing of the subtitles

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

#478 - usage of new added parameters (repetition_penalty and no_repeat_ngram_size)

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

#477 - why faster-whiser vad default parameters are much different from silero-vad

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

#476 - Add property WhisperModel.supported_languages

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

#475 - Expose function available_models

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

#474 - adding initial_prompt is changing the segment duration

Issue - State: open - Opened by abdulnim about 1 year ago - 3 comments

#473 - How to run faster_whisper on multiple GPUs？

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

#472 - Support Baichuan2?

Issue - State: closed - Opened by lx0126z about 1 year ago - 1 comment

#471 - How to do multi-GPU computing?

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

#469 - Update tokenizers requirement to include version 0.14

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

#468 - Always run the encoder at the beginning of the loop

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

#467 - added content_frames field

Pull Request - State: closed - Opened by jhj0517 about 1 year ago - 2 comments

#466 - Improve error message for invalid task and language parameters

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

#465 - Transcriptions with repeated sentences

Issue - State: open - Opened by bfavero about 1 year ago - 9 comments

#463 - Add more details about the requirements in the README

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

#461 - Hugging Face `open_asr_leaderboard`

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

#457 - How to convert faster-whisper model to torchscript format?

Issue - State: closed - Opened by 12-zhx about 1 year ago - 3 comments

#456 - Playing with faster-whisper audio segmentation. How does it work ?

Issue - State: open - Opened by Lorenzoncina about 1 year ago - 1 comment

#455 - Bug since today (0.8.0 ?) with load_model

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

#453 - Add "large" alias for "large-v2" model

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

#452 - How to output longer segments?

Issue - State: open - Opened by DONAMO-163 about 1 year ago - 6 comments