xenova/whisper-web issues and pull requests

#45 - Output always just '!!!!!!!'

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

#44 - Feature Request: instead of "transcript.(txt|json)", name output file to the input file's name

Issue - State: open - Opened by shola about 2 months ago

#43 - Feature: Word timestamp

Issue - State: open - Opened by mena234 2 months ago

#42 - The data is not on CPU. Use `getData()` to download GPU data to CPU, or use `texture` or `gpuBuffer` property to access the GPU data directly.

Issue - State: open - Opened by raodaqi 5 months ago

#41 - WebGPU pipeline supporting word-level timestamps

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

#40 - feature: Streaming mode in demo

Issue - State: open - Opened by asideofcode-dev 5 months ago - 3 comments

#39 - The issue with exporting the txt format

Issue - State: open - Opened by midpoint 5 months ago

#38 - Repeat output

Issue - State: open - Opened by ycjcl868 5 months ago

#37 - config the model and audio file cache dir!

Issue - State: open - Opened by meicale 5 months ago

#36 - Is there an API?

Issue - State: open - Opened by TonySimonovsky 5 months ago - 1 comment

#35 - The video in the description doesnt have sound

Issue - State: open - Opened by Ulf3000 5 months ago - 1 comment

#34 - Setting language or other parameters

Issue - State: open - Opened by stevevaius2015 5 months ago - 1 comment

#33 - Missing License

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

#32 - Speech Recognition/Whisper word level scores or confidence output

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

#31 - Realtime transcribe / streaming support?

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

#30 - Vanilla JS example

Issue - State: open - Opened by flatsiedatsie 8 months ago - 3 comments

#29 - (° - ° ) help needed for client/server code isolation

Issue - State: open - Opened by papiche 9 months ago

#28 - Save fully processed chunks to optimize decoding

Pull Request - State: closed - Opened by shopped 9 months ago - 1 comment

#27 - Whisper

Issue - State: closed - Opened by add54 9 months ago

#26 - It's possible send a prompt to the transcriber?

Issue - State: open - Opened by ulisseshen 9 months ago

#25 - user large v3 online?

Issue - State: open - Opened by johnfelipe 12 months ago - 2 comments

#24 - Uncaught (in promise) Error: Unsupported model type: whisper

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

#23 - Doesn't it work on mobiles? Android, iPhone

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

#22 - Chrome Extension Empty Output

Issue - State: open - Opened by pythonlearner1025 about 1 year ago - 1 comment

#21 - Receiving Error on Hugginface implementation

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

#20 - Not correctly conversion in one word or short audio and autocorrection in long audio

Issue - State: open - Opened by Exoways123 about 1 year ago - 1 comment

#20 - Not correctly conversion in one word or short audio and autocorrection in long audio

Issue - State: open - Opened by Exoways123 about 1 year ago - 1 comment

#19 - Error code = 6

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

#19 - Error code = 6

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

#18 - Large model

Issue - State: open - Opened by mootje2 about 1 year ago - 3 comments

#17 - Word-level-timestamps

Issue - State: open - Opened by christopher-kapic about 1 year ago - 2 comments
Labels: enhancement, help wanted, good first issue

#17 - Word-level-timestamps

Issue - State: open - Opened by christopher-kapic about 1 year ago - 2 comments
Labels: enhancement, help wanted, good first issue

#16 - Streaming support

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

#16 - Streaming support

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

#15 - Could not locate file model.onnx

Issue - State: closed - Opened by harryradford over 1 year ago - 2 comments

#15 - Could not locate file model.onnx

Issue - State: closed - Opened by harryradford over 1 year ago - 2 comments

#14 - can not support chinese recognize

Issue - State: open - Opened by Pandas886 over 1 year ago - 2 comments

#13 - Add SRT export

Pull Request - State: open - Opened by PushpenderSaini0 over 1 year ago - 2 comments

#12 - add try example on front

Pull Request - State: open - Opened by radames over 1 year ago

#12 - add try example on front

Pull Request - State: open - Opened by radames over 1 year ago

#11 - Please Add SRT export or download button

Issue - State: open - Opened by Tsogtpurev over 1 year ago - 3 comments
Labels: help wanted, good first issue

#11 - Please Add SRT export or download button

Issue - State: open - Opened by Tsogtpurev over 1 year ago - 3 comments
Labels: help wanted, good first issue

#10 - feat: adding whisper web

Pull Request - State: closed - Opened by albertsyh over 1 year ago - 2 comments

#10 - feat: adding whisper web

Pull Request - State: closed - Opened by albertsyh over 1 year ago - 2 comments

#9 - Update README.md for firefox users

Pull Request - State: closed - Opened by PushpenderSaini0 over 1 year ago - 1 comment

#9 - Update README.md for firefox users

Pull Request - State: closed - Opened by PushpenderSaini0 over 1 year ago - 1 comment

#8 - Development in firefox instruction

Issue - State: closed - Opened by PushpenderSaini0 over 1 year ago - 4 comments