Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Feat] Add qwen2_audio model support and Automatic speech recognition task with LibriSpeech dataset #289

Merged
merged 3 commits into from
Oct 1, 2024
Merged

[Feat] Add qwen2_audio model support and Automatic speech recognition task with LibriSpeech dataset #289

merged 3 commits into from
Oct 1, 2024

Conversation

Prophet-C
Copy link
Contributor

[Feat] Add qwen2_audio model support
[Feat] Add Automatic speech recognition (ASR) task with LibriSpeech dataset
[Feat] Add evalutation metric word error rate (WER) for ASR task

[Need Check] require new packages to be installed for evaluation on ASR evaluation (no specific version required): zhconv, editdistance, more_itertools

@Luodian
Copy link
Contributor

Luodian commented Sep 30, 2024

Thanks for this PR, seems linting not passed.

You may consider use pre-commit and execute pre-commit run --all-files

@Luodian Luodian changed the base branch from main to feat-dev September 30, 2024 15:51
@Luodian Luodian merged commit 4b7ccea into EvolvingLMMs-Lab:feat-dev Oct 1, 2024
1 check passed
kcz358 pushed a commit that referenced this pull request Oct 16, 2024
@Prophet-C @kcz358
[Feat] Add qwen2_audio model support and Automatic speech recognition…
95b619d 
… task with LibriSpeech dataset (#289)

* "add qwen2_audio model, asr librispeech eval task"

* lint update for PR #289

---------

Co-authored-by: Pengyun <u7978909@anu.edu.au>
kcz358 pushed a commit that referenced this pull request Oct 26, 2024
@Prophet-C @kcz358
[Feat] Add qwen2_audio model support and Automatic speech recognition…
e298464 
… task with LibriSpeech dataset (#289)

* "add qwen2_audio model, asr librispeech eval task"

* lint update for PR #289

---------

Co-authored-by: Pengyun <u7978909@anu.edu.au>
kcz358 pushed a commit that referenced this pull request Nov 23, 2024
@Prophet-C @kcz358
[Feat] Add qwen2_audio model support and Automatic speech recognition…
2757bab 
… task with LibriSpeech dataset (#289)

* "add qwen2_audio model, asr librispeech eval task"

* lint update for PR #289

---------

Co-authored-by: Pengyun <u7978909@anu.edu.au>
kcz358 pushed a commit that referenced this pull request Nov 27, 2024
@Prophet-C @kcz358
[Feat] Add qwen2_audio model support and Automatic speech recognition…
3e53152 
… task with LibriSpeech dataset (#289)

* "add qwen2_audio model, asr librispeech eval task"

* lint update for PR #289

---------

Co-authored-by: Pengyun <u7978909@anu.edu.au>
kcz358 added a commit that referenced this pull request Nov 27, 2024
@kcz358 @Prophet-C
@pbcong @Luodian @Yingluo-momo @pufanyi @KairuiHu
[Release] lmms-eval v0.3.0 release (#428)
0cee464 
* [Feat] Add qwen2_audio model support and Automatic speech recognition task with LibriSpeech dataset (#289)

* "add qwen2_audio model, asr librispeech eval task"

* lint update for PR #289

---------

Co-authored-by: Pengyun <u7978909@anu.edu.au>

* add clotho_aqa task

* Apply black formatting

* formatting

* excluding xl due to downloading issue.

* [Feat] add audiobench version of clothoaqa (#302)

* add clothoaqa task

* formatting

* minor fixes

* minor fixes

* Add AIR_bench task (#315)

* add air_bench

* minor changes

* add common_voice_15 and people_speech tasks (#316)

Co-authored-by: Pengyun <u7978909@anu.edu.au>

* add indent to yaml

* Add openhermes task (#323)

* add openhermes task

* formatting

* [Refactor] Fixing doc to audio return type, qwen_audio revise (#329)

* Add downsample function for audio array

* Batch support for qwen2 and use apply chat template

* Return sr for common voice

* Doc to audio to return the whole dict

* add muchomusic and vocalsound task (#331)

* add alpaca audio task (#333)

* [feat] added gigaspeech config (#334)

* fix xl yaml

* Fixed config for gigaspeech_xl. gigaspeech_xl_test has intermittent problem.

* add alpaca audio task (#333)

* pre-committed utils.py

---------

Co-authored-by: Cong <101887866+pbcong@users.noreply.github.com>

* add tedlium_long_form and tedlium_dev_test tasks (#345)

Co-authored-by: Pengyun <u7978909@anu.edu.au>

* [Feat] add-wavcaps (#349)

* fix xl yaml

* Fixed config for gigaspeech_xl. gigaspeech_xl_test has intermittent problem.

* add alpaca audio task (#333)

* pre-committed utils.py

* add wavcaps

* add wavcaps

---------

Co-authored-by: Cong <101887866+pbcong@users.noreply.github.com>

* Update dep and fix log samples for audio (#355)

* Update dep

* Fix saved audio OOM error

* Fix typing

* Fix librispeech dataset name

* Add add_generation_prompt as option for Qwen audio

* Add add system propmt as optional

* fix vocalsound (#362)

* Add using simple prompt for Qwen2 Audio to align (#360)

* Add retry for gpt api call and improve air_bench aggregation function (#376)

* add retry for api calls and change air_bench_foundation aggregation function

* make azure default api

* minor changes

* [Feat] Add mix_evals audio2text (#420)

* Add mix_evals audio2text

* Fix task tags in datasets

* Gemini Audio (#421)

* gemini audio

* better variable naming

* Revise prompt

* delete redundant tasks in gigaspeech

* Fix wavcaps bugs

* Add lmms-eval-0.3 docs

Update lmms-eval-0.3.md

fix errors in markdown and add hyperlinks

proofread markdown and fix errors

rewrite some parts to fix errors

rewrite some parts to fix errors

rewrite some parts to fix errors

try optimize the table format using html

try optimize the table format using html

try optimize the table 2 format

final proofread

final proofread

final proofread

add explanantion for AIF and ASR

standardize WER to WER(↓)

final proofread

final proofread

final proofread

final proofread

correct hyperlink errors

modify readme to support lmms-eval0.3.0 release

modify icon

fix typos

Co-Authored-By: KairuiHu <kairuih12@gmail.com>

---------

Co-authored-by: Pengyun Wang <91826032+Prophet-C@users.noreply.github.com>
Co-authored-by: Pengyun <u7978909@anu.edu.au>
Co-authored-by: pbcong <congphamba2005@gmail.com>
Co-authored-by: Li Bo <drluodian@gmail.com>
Co-authored-by: Cong <101887866+pbcong@users.noreply.github.com>
Co-authored-by: Yingluo <liyingluo57@gmail.com>
Co-authored-by: Totoluo <52833580+Yingluo-momo@users.noreply.github.com>
Co-authored-by: Pu Fanyi <FPU001@e.ntu.edu.sg>
Co-authored-by: KairuiHu <kairuih12@gmail.com>
ZhaoCinyu pushed a commit to ZhaoCinyu/lmms-eval that referenced this pull request Dec 9, 2024
@kcz358 @Prophet-C
@pbcong @Luodian @Yingluo-momo @pufanyi @KairuiHu @ZhaoCinyu
[Release] lmms-eval v0.3.0 release (EvolvingLMMs-Lab#428)
ac06e38 
* [Feat] Add qwen2_audio model support and Automatic speech recognition task with LibriSpeech dataset (EvolvingLMMs-Lab#289)

* "add qwen2_audio model, asr librispeech eval task"

* lint update for PR EvolvingLMMs-Lab#289

---------

Co-authored-by: Pengyun <u7978909@anu.edu.au>

* add clotho_aqa task

* Apply black formatting

* formatting

* excluding xl due to downloading issue.

* [Feat] add audiobench version of clothoaqa (EvolvingLMMs-Lab#302)

* add clothoaqa task

* formatting

* minor fixes

* minor fixes

* Add AIR_bench task (EvolvingLMMs-Lab#315)

* add air_bench

* minor changes

* add common_voice_15 and people_speech tasks (EvolvingLMMs-Lab#316)

Co-authored-by: Pengyun <u7978909@anu.edu.au>

* add indent to yaml

* Add openhermes task (EvolvingLMMs-Lab#323)

* add openhermes task

* formatting

* [Refactor] Fixing doc to audio return type, qwen_audio revise (EvolvingLMMs-Lab#329)

* Add downsample function for audio array

* Batch support for qwen2 and use apply chat template

* Return sr for common voice

* Doc to audio to return the whole dict

* add muchomusic and vocalsound task (EvolvingLMMs-Lab#331)

* add alpaca audio task (EvolvingLMMs-Lab#333)

* [feat] added gigaspeech config (EvolvingLMMs-Lab#334)

* fix xl yaml

* Fixed config for gigaspeech_xl. gigaspeech_xl_test has intermittent problem.

* add alpaca audio task (EvolvingLMMs-Lab#333)

* pre-committed utils.py

---------

Co-authored-by: Cong <101887866+pbcong@users.noreply.github.com>

* add tedlium_long_form and tedlium_dev_test tasks (EvolvingLMMs-Lab#345)

Co-authored-by: Pengyun <u7978909@anu.edu.au>

* [Feat] add-wavcaps (EvolvingLMMs-Lab#349)

* fix xl yaml

* Fixed config for gigaspeech_xl. gigaspeech_xl_test has intermittent problem.

* add alpaca audio task (EvolvingLMMs-Lab#333)

* pre-committed utils.py

* add wavcaps

* add wavcaps

---------

Co-authored-by: Cong <101887866+pbcong@users.noreply.github.com>

* Update dep and fix log samples for audio (EvolvingLMMs-Lab#355)

* Update dep

* Fix saved audio OOM error

* Fix typing

* Fix librispeech dataset name

* Add add_generation_prompt as option for Qwen audio

* Add add system propmt as optional

* fix vocalsound (EvolvingLMMs-Lab#362)

* Add using simple prompt for Qwen2 Audio to align (EvolvingLMMs-Lab#360)

* Add retry for gpt api call and improve air_bench aggregation function (EvolvingLMMs-Lab#376)

* add retry for api calls and change air_bench_foundation aggregation function

* make azure default api

* minor changes

* [Feat] Add mix_evals audio2text (EvolvingLMMs-Lab#420)

* Add mix_evals audio2text

* Fix task tags in datasets

* Gemini Audio (EvolvingLMMs-Lab#421)

* gemini audio

* better variable naming

* Revise prompt

* delete redundant tasks in gigaspeech

* Fix wavcaps bugs

* Add lmms-eval-0.3 docs

Update lmms-eval-0.3.md

fix errors in markdown and add hyperlinks

proofread markdown and fix errors

rewrite some parts to fix errors

rewrite some parts to fix errors

rewrite some parts to fix errors

try optimize the table format using html

try optimize the table format using html

try optimize the table 2 format

final proofread

final proofread

final proofread

add explanantion for AIF and ASR

standardize WER to WER(↓)

final proofread

final proofread

final proofread

final proofread

correct hyperlink errors

modify readme to support lmms-eval0.3.0 release

modify icon

fix typos

Co-Authored-By: KairuiHu <kairuih12@gmail.com>

---------

Co-authored-by: Pengyun Wang <91826032+Prophet-C@users.noreply.github.com>
Co-authored-by: Pengyun <u7978909@anu.edu.au>
Co-authored-by: pbcong <congphamba2005@gmail.com>
Co-authored-by: Li Bo <drluodian@gmail.com>
Co-authored-by: Cong <101887866+pbcong@users.noreply.github.com>
Co-authored-by: Yingluo <liyingluo57@gmail.com>
Co-authored-by: Totoluo <52833580+Yingluo-momo@users.noreply.github.com>
Co-authored-by: Pu Fanyi <FPU001@e.ntu.edu.sg>
Co-authored-by: KairuiHu <kairuih12@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Luodian Luodian Luodian approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@Prophet-C @Luodian