wav2letter
wav2letter copied to clipboard
flashlight
Facebook AI Research's Automatic Speech Recognition Toolkit
Bumps [mako](https://github.com/sqlalchemy/mako) from 1.1.0 to 1.2.2. Release notes Sourced from mako's releases. 1.2.2 Released: Mon Aug 29 2022 bug [bug] [lexer] Fixed issue in lexer where the regexp used to...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [certifi](https://github.com/certifi/python-certifi) from 2019.11.28 to 2023.7.22. Commits 8fb96ed 2023.07.22 afe7722 Bump actions/setup-python from 4.6.1 to 4.7.0 (#230) 2038739 Bump dessant/lock-threads from 3.0.0 to 4.0.1 (#229) 44df761 Hash pin Actions and...
Bumps [future](https://github.com/PythonCharmers/python-future) from 0.18.2 to 0.18.3. Release notes Sourced from future's releases. v0.18.3 This is a minor bug-fix release containing a number of fixes: Backport fix for bpo-38804 (c91d70b) Fix...
Bumps [requests](https://github.com/psf/requests) from 2.22.0 to 2.31.0. Release notes Sourced from requests's releases. v2.31.0 2.31.0 (2023-05-22) Security Versions of Requests between v2.3.0 and v2.30.0 are vulnerable to potential forwarding of Proxy-Authorization...
Hello, I have recently installed wav2letter v0.2 on ubuntu 18.04. I am now trying to continue training with the pretrained dev-clean transformer models from sota/2019 recipe for only 1 epoch....
### Bug Description The link of the Dict fairseq for the word level GCNN listed in this [table](https://github.com/flashlight/wav2letter/tree/main/recipes/sota/2019#pre-trained-language-models) does not work. #### Reproduction Steps The link points to this [address](https://dl.fbaipublicfiles.com/wav2letter/lexicon_free/librispeech/models/lm/lm_librispeech_convlm_word_14B.dict)...
### Question I have read the paper and have some questions. In thisr paper MLS: A LARGE-SCALE MULTILINGUAL DATASET FOR SPEECH RESEARCH, a 36-layers transformer was used to train the...
Hi, I am looking to use pretrained wav2letter and I got to this link having pretrained weights, https://github.com/flashlight/wav2letter/tree/wav2letter-lua?tab=readme-ov-file#pre-trained-models but the links are broken, I am not able to download the...
Summary: X-link: https://github.com/flashlight/flashlight/pull/1176 X-link: https://github.com/pytorch/FBGEMM/pull/3242 Converts the directory specified to use the Ruff formatter in pyfmt ruff_dog If this diff causes merge conflicts when rebasing, please run `hg status -n...
Metadata
Owner
Metadata
Facebook AI Research's Automatic Speech Recognition Toolkit