facebookresearch/fairseq
1
1
Fork 0
mirror of https://github.com/facebookresearch/fairseq.git synced 2024-09-11 17:25:31 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix model link (#2408)

Browse Source 
Summary:
# Before submitting

- [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements)
- [ ] Did you read the [contributor guideline](https://github.com/pytorch/fairseq/blob/main/CONTRIBUTING.md)?
- [ ] Did you make sure to update the docs?
- [ ] Did you write any new necessary tests?

## What does this PR do?
Fixes # (issue).

## PR review
Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

## Did you have fun?
Make sure you had fun coding �

Pull Request resolved: https://github.com/fairinternal/fairseq-py/pull/2408

Reviewed By: alexeib

Differential Revision: D31422844

Pulled By: xuqiantong

fbshipit-source-id: 348050118621de922c08632ca7f31dedba109da1
This commit is contained in:
Qiantong Xu 2021-10-05 21:19:16 -07:00 committed by Facebook GitHub Bot
parent 6639842016
commit dd3bd3c049
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/wav2vec/README.md
View File

@ -55,7 +55,7 @@ We also finetuned XLSR-53 on languages from [CommonVoice](https://commonvoice.mo
Pretrained Model | Fintune Dataset | # Languages | Phonemizer | Model | Dictionary
|---|---|---|---|---|---
XLSR-53 | CommonVoice | 26 | [Espeak](https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md) | [download](https://dl.fbaipublicfiles.com/fairseq/zero_shot/espeak_26lang_m10.pt) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/zero_shot/espeak_dict.txt)
XLSR-53 | CommonVoice | 26 | [Espeak](https://github.com/espeak-ng/espeak-ng/blob/master/docs/languages.md) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/zero_shot/espeak_26lang_m10.pt) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/zero_shot/espeak_dict.txt)
XLSR-53 | CommonVoice | 21 | [Phonetisaurus](https://github.com/AdolfVonKleist/Phonetisaurus) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/zero_shot/phonetisaurus_21lang_m10.pt) | [download](https://dl.fbaipublicfiles.com/fairseq/wav2vec/zero_shot/phonetisaurus_dict.txt)
We release 2 models that are finetuned on data from 2 different phonemizers. Although the phonemes are all [IPA](https://en.wikipedia.org/wiki/International_Phonetic_Alphabet) symbols, there are still subtle differences between the phonemized transcriptions from the 2 phonemizers. Thus, it's better to use the corresponding model, if your data is phonemized by either phonemizer above.