-
Notifications
You must be signed in to change notification settings - Fork 26.5k
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.
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
[MMS] Update docs with HF TTS implementation #25907
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Very cool! 🔥
The documentation is not available anymore as the PR was closed or merged. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks! Left a few doc nits 😉
Audio(waveform, rate=model.config.sampling_rate) | ||
``` | ||
|
||
For certain languages with non-Roman alphabets, such as Arabic, Mandarin or Hindi, the [`uroman`](https://github.com/isi-nlp/uroman) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For certain languages with non-Roman alphabets, such as Arabic, Mandarin or Hindi, the [`uroman`](https://github.com/isi-nlp/uroman) | |
- For certain languages with non-Roman alphabets, such as Arabic, Mandarin or Hindi, the [`uroman`](https://github.com/isi-nlp/uroman) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why add a bullet point here?
If required, you should apply the uroman package to your text inputs **prior** to passing them to the `VitsTokenizer`, | ||
since currently the tokenizer does not support performing the pre-processing itself. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do you think we should add this? With a if self.is_uroman: requires_backend
? Makes sense no?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you also add an example of how to do this pre-processing?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It's a perl package, not a Python package, so we can't import it. The only way of running uroman is through the command line, see discussion here: #24085 (comment)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Added an example for pre-processing: d264692
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* [MMS] Update docs with HF TTS implementation * Update docs/source/en/model_doc/mms.md Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * add uromanise to docs --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* [MMS] Update docs with HF TTS implementation * Update docs/source/en/model_doc/mms.md Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * add uromanise to docs --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
* [MMS] Update docs with HF TTS implementation * Update docs/source/en/model_doc/mms.md Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * add uromanise to docs --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
What does this PR do?
Following #24085, Transformers now contains an implementation of MMS-TTS. This PR updates the MMS docs to include a code-snippet using this implementation.
cc @osanseviero since this was something you flagged before, and also @Vaibhavs10 for viz