Ecosyste.ms: Issues

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

GitHub / huggingface/distil-whisper issues and pull requests

#59 - Accelerate

Issue - State: open - Opened by wntg 12 months ago - 1 comment

#59 - Accelerate

Issue - State: open - Opened by wntg 12 months ago - 1 comment

#58 - Training without real labels

Issue - State: open - Opened by rolisz 12 months ago - 1 comment

#58 - Training without real labels

Issue - State: open - Opened by rolisz 12 months ago - 1 comment

#57 - Can fine tuning for phoneme task?

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

#57 - Can fine tuning for phoneme task?

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

#54 - [Question] Mixed Speech transcription

Issue - State: open - Opened by Tejaswgupta 12 months ago - 5 comments

#54 - [Question] Mixed Speech transcription

Issue - State: open - Opened by Tejaswgupta 12 months ago - 5 comments

#53 - small uses more memory (but is faster) than medium (ONNX quantized)

Issue - State: closed - Opened by kmn1024 12 months ago - 5 comments

#53 - small uses more memory (but is faster) than medium (ONNX quantized)

Issue - State: closed - Opened by kmn1024 12 months ago - 5 comments

#52 - Fix regex in `get_last_checkpoint`

Pull Request - State: closed - Opened by bofenghuang 12 months ago - 1 comment

#52 - Fix regex in `get_last_checkpoint`

Pull Request - State: closed - Opened by bofenghuang 12 months ago - 1 comment

#51 - Fix total_train_steps issue related to gradient_accumulation_steps

Pull Request - State: closed - Opened by bofenghuang 12 months ago - 2 comments

#51 - Fix total_train_steps issue related to gradient_accumulation_steps

Pull Request - State: closed - Opened by bofenghuang 12 months ago - 2 comments

#50 - Could distil-whisper load local speech dataset?

Issue - State: open - Opened by shuaijiang 12 months ago - 7 comments

#50 - Could distil-whisper load local speech dataset?

Issue - State: open - Opened by shuaijiang 12 months ago - 7 comments

#49 - How to make training data?

Issue - State: open - Opened by satani99 12 months ago - 1 comment

#49 - How to make training data?

Issue - State: open - Opened by satani99 12 months ago - 1 comment

#48 - .

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

#48 - .

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

#46 - How can I generate SRT file ?

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

#46 - How can I generate SRT file ?

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

#45 - Why we need KL-divergence

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

#45 - Why we need KL-divergence

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

#44 - DDP updates

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

#44 - DDP updates

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

#43 - small readme updates

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

#43 - small readme updates

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

#42 - Improve readme training

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

#42 - Improve readme training

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

#41 - Streaming Implementation of Distil Whisper

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

#41 - Streaming Implementation of Distil Whisper

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

#40 - Does this use FSDP or Deepspeed? Req. for accelerate config

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

#40 - Does this use FSDP or Deepspeed? Req. for accelerate config

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

#39 - quick readme updates

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

#39 - quick readme updates

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

#38 - Update readme with training code refs

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

#38 - Update readme with training code refs

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

#37 - Add training code

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

#37 - Add training code

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

#36 - Is this supposed to support large-v3?

Issue - State: closed - Opened by captainyugi00 about 1 year ago - 15 comments

#36 - Is this supposed to support large-v3?

Issue - State: closed - Opened by captainyugi00 about 1 year ago - 15 comments

#35 - Smaller models?

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

#35 - Smaller models?

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

#34 - How long of an Audio Clip can the model transcribe at once?

Issue - State: closed - Opened by Aryan-401 about 1 year ago - 2 comments

#34 - How long of an Audio Clip can the model transcribe at once?

Issue - State: closed - Opened by Aryan-401 about 1 year ago - 2 comments

#33 - Long-Form transcription with Faster Whisper

Issue - State: open - Opened by 9throok about 1 year ago - 3 comments

#33 - Long-Form transcription with Faster Whisper

Issue - State: open - Opened by 9throok about 1 year ago - 3 comments

#32 - Could you add Required VRAM info in the README?

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

#32 - Could you add Required VRAM info in the README?

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

#31 - Sentence separation

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

#31 - Sentence separation

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

#30 - Running medium.en model on Jetson Xavier

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

#30 - Running medium.en model on Jetson Xavier

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

#29 - stream-whisper

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

#29 - stream-whisper

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

#27 - timestamp for utterance or sentence?

Issue - State: open - Opened by chenrq2005 about 1 year ago - 5 comments

#27 - timestamp for utterance or sentence?

Issue - State: open - Opened by chenrq2005 about 1 year ago - 5 comments

#26 - beamsize > 1

Issue - State: open - Opened by GuoYi0 about 1 year ago - 7 comments

#26 - beamsize > 1

Issue - State: open - Opened by GuoYi0 about 1 year ago - 7 comments

#25 - Long form transcription with model.generate

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

#24 - When will the training code be released？

Issue - State: closed - Opened by GuoYi0 about 1 year ago - 3 comments

#24 - When will the training code be released？

Issue - State: closed - Opened by GuoYi0 about 1 year ago - 3 comments

#23 - Hopefully the large-v3 version will be supported

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

#23 - Hopefully the large-v3 version will be supported

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

#22 - [For your information] Run onnx models of distil-whisper with sherpa-onnx

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

#22 - [For your information] Run onnx models of distil-whisper with sherpa-onnx

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

#21 - is it possible to train it with own dataset for kazakh language?

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

#20 - initial_prompt support?

Issue - State: open - Opened by silvacarl2 about 1 year ago - 6 comments

#19 - Update README.md

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

#18 - distil-whisper doesn't work as a drop-in replacement for whisper

Issue - State: closed - Opened by o-alexandre-felipe about 1 year ago - 4 comments

#17 - Is it possible to use this with 'faster_whisper'

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

#16 - How to use ONNX model?

Issue - State: open - Opened by H-G-11 about 1 year ago - 2 comments

#15 - Is it possible to run the model to recognize other languages?

Issue - State: closed - Opened by sanek11591 about 1 year ago - 2 comments

#14 - Tiny model?

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

#13 - Export subtitle format of vtt

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

#12 - Further README updates

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

#10 - Missing config.json file

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

#9 - Improve README a bit

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

#8 - Where is the model?

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

#7 - Is it available for Commercial Use?

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

#6 - english only for large-v2?

Issue - State: open - Opened by ostegm about 1 year ago - 10 comments

#5 - Distillation code and calibration data

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

#4 - example using microphone

Issue - State: open - Opened by AwokeKnowing about 1 year ago - 11 comments

#3 - Compatibility with CTranslate2 / faster-whisper

Issue - State: open - Opened by entn-at about 1 year ago - 8 comments

#2 - Changed Oct -:>. November!

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

#1 - Fix typo in release dates

Pull Request - State: closed - Opened by IbrahimAmin1 about 1 year ago