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

Add speech2text model for offline #614

Open
wants to merge 596 commits into
base: offline-recognition
Choose a base branch
from
Open

Add speech2text model for offline #614

wants to merge 596 commits into from

Conversation

dellano54
Copy link

@dellano54 dellano54 commented Jun 22, 2022 •
edited
Loading

Try using speech2text than pocketsphinx because its more efficient, faster, accurate and pre-trained in large dataset

ftnext and others added 30 commits December 6, 2023 01:04
@ftnext
[test] recognize_legacy
54bb083
@ftnext
[test] Add parameter specified case
e70d466
@ftnext
[refactor] Not return empty list; raise error
e72ae1f
@ftnext
[refactor] Raise error in find_best_hypothesis
e4e3caa
@ftnext
[bugfix] Missing ValueError
368a7ef
@ftnext
[refactor] convert_to_result raises error when result is invalid
fa8e166
@ftnext
[chore] Run doctest too
140b469
@ftnext
[refactor] Remove first large test
f69243f
@ftnext
Merge pull request #721 from ftnext/i719-refactor-google
594d7cd 
Refactor recognize_google
@ftnext
[chore] Bump up 3.10.1; Support Python 3.11
1b737c5
@yackermann
Updated to the latest OpenAI API changes, and fixed #720
50e006b
@HideyoshiNakazone
Adds Parameter use_enhanced and model to GoogleCloudSpeech
c845904 
Adds the parameters use_enhanced and model to the recognize_google_cloud method for more customizable options for the user and better results in specific cases
@ftnext
style: name based OpenAI document (minimum diff)
42668ba
@ftnext
test: Tweak expected for latest Whisper
9a694d7
@ftnext
Merge pull request #729 from herrjemand/herrjemand-oai-whisper-api-fix
4a5b375 
Updated to the latest OpenAI API changes, and fixed #720
@ftnext
[chore] Bump up 3.10.2; Support openai-python 1.x
c028409
@ftnext
[test] Add Whisper API normal case
dd97ae8
@ftnext
[test] Add Whisper API another normal case
105daa1
@ftnext
[chore] Install for added tests
3258e25
@ftnext
Merge pull request #738 from ftnext/test-whisper-api
4924857 
[test] Add tests for recognize_whisper_api
@ftnext
[chore] Install whisper package from PyPI
43ee24b
@ftnext
[test] Add openai-whisper test case with mock
a742862
@ftnext
[test] recognize_whisper(show_dict=True)
a869cc3
@ftnext
[test] Specify paramters of recognize_whisper
4afaa52
@ftnext
[test] Remove cases with actual models
4c48ed6
@ftnext
[docs] Install openai-whisper from PyPI
8da6e42
@ftnext
Merge pull request #739 from ftnext/test-whisper
9194a47
@ftnext
[chore] Add extra for openai-whisper
5e7432c
@ftnext
[chore] Refactor using extras
f294669
@ftnext
[docs] Install whisper dependencies by specifying extra
863b10a
ftnext added 30 commits December 30, 2024 14:00
@ftnext
[refactor] Reduce mock in whisper tests
cbca8b9
@ftnext
[refactor] Test class to add other case easier
7df1253
@ftnext
[test] GPU available case
36b0464
@ftnext
[feat] Specify transcribe's parameters
3dbbe17
@ftnext
[refactor] Extract AudioData fixture
2ee6044
@ftnext
[refactor] Patch sf.read as fixture
4dd2985
@ftnext
[refactor] Extract mock creation into fixtures
8b2d91c
@ftnext
[docs] Add type hints
d502a2e
@ftnext
[chore] faster-whisper extra
5da7fdf
@ftnext
[docs] Add parameters' type hint
5c34084
@ftnext
[bugfix] show_dict=True
5f55e92
@ftnext
[docs] Add docstring
a422db0
@ftnext
[docs] Add faster_whisper in reference
ec8d05f
@ftnext
[feat] Users can call Recognizer.recognize_faster_whisper()
4f2506a
@ftnext
[docs] faster-whisper installation
e23338a
@ftnext
[bugfix] Install numpy in dev environment
3fea948 
* Fix Ubuntu 3.13 failed: ModuleNotFoundError: No module named 'numpy'
@ftnext
[bugfix] Run (=skip) tests without faster-whisper
070d02f
@ftnext
[feat] Use device="auto" (default)
0edcc43
@ftnext
[feat] Run manually as e2e
ef69c4a 
python -m speech_recognition.recognizers.whisper_local.faster_whisper
@ftnext
[feat] Enable to specify initialization parameters
ac556c1
@ftnext
[docs] Fix type hint
e663cb0
@ftnext
Merge pull request #814 from ftnext/feature/faster-whisper
dd67b7c 
Support Faster Whisper (with less copy and paste)
@ftnext
[chore] Remove recognize_whisper_api (Use recognize_openai instead)
94f0f55
@ftnext
Merge pull request #815 from ftnext/chore/remove-recognize-whisper-api
bcd4266 
Remove `recognize_whisper_api` (Use `recognize_openai` instead)
@ftnext
chore: Make copyright year of license not need to update
b795baf
@ftnext
Merge pull request #818 from ftnext/chore/copyright-year
f2fc4f7 
chore: Make copyright year of license not need to update
@ftnext
Bump up 3.14.0
71cacd8
@ftnext
bugfix: Pass CI (ubuntu-latest is now 24.04)
8afab68 
It seems pre-installed swig version mismatch
@ftnext
bugfix: missing replace
cd5f4c4
@ftnext
Merge pull request #820 from Uberi/hotfix-pocketsphinx-test-failure
e4af8de 
hotfix: Pass CI to release 3.14.0
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
7 participants
@dellano54 @ftnext @yackermann @HideyoshiNakazone @clusterfudge @Uberi @cclauss