facebookresearch/fairseq
1
1
Fork 0
mirror of https://github.com/facebookresearch/fairseq.git synced 2024-11-20 18:41:02 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update MMS README (#5115)

Browse Source
This commit is contained in:
Vineel Pratap 2023-05-22 12:40:22 -07:00 committed by GitHub
parent aec128cb70
commit c7bfa9bbc3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
examples/mms/README.md
View File

@ -156,6 +156,11 @@ $ PYTHONPATH='.' python3 examples/mms/lid/infer.py /path/to/dict/l126/ --path
The above command assumes there is a file named `dict.lang.txt` in `/path/to/dict/l126/`. `<OUTDIR>/predictions.txt` will contain the predictions from the model for the audio files in `manifest.tsv`.
## Forced Alignment Tooling
We also developed an efficient forced alignment algorithm implemented on GPU which is able to process very long audio files. This algorithm is open sourced and we provide instructions on how to use it [here](data_prep). We also open source a multilingual alignment model trained on 31K hours of data in 1,130 languages, as well as text normalization scripts.
# License
The MMS code and model weights are released under the CC-BY-NC 4.0 license.