Conversation
Signed-off-by: subhankar-ghosh <subhankar2321@gmail.com>
subhankar-ghosh
changed the title
subhankar-ghosh
added
documentation
|
[🤖]: Hi @subhankar-ghosh 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully. So it might be time to merge this PR or get some approvals. |
There was a problem hiding this comment.
Pull request overview
This PR adds comprehensive documentation for Magpie-TTS, a hallucination-free text-to-speech system developed by NVIDIA that uses monotonic alignment techniques to ensure robust speech synthesis.
Changes:
- Added main Magpie-TTS documentation covering architecture, features, training, and inference
- Added preference optimization guide detailing DPO and GRPO training approaches
- Added longform inference guide explaining multi-sentence speech generation
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| docs/source/tts/magpietts.rst | Main documentation covering model architecture, key features, training, inference, and resources |
| docs/source/tts/magpietts-po.rst | Detailed guide on preference optimization techniques (DPO and GRPO) for quality improvement |
| docs/source/tts/magpietts-longform.rst | Guide for generating speech from long text inputs with sentence-level chunking |
| docs/source/tts/intro.rst | Updated table of contents to include the three new Magpie-TTS documentation pages |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| Preference Optimization | ||
| ----------------------- |
There was a problem hiding this comment.
Should we have this section or just link to the po doc?
There was a problem hiding this comment.
I was trying to make this as the one Readme that has all information, and if someone needs more details then they go to the po doc. That was the idea.
There was a problem hiding this comment.
Maybe we should just describe the methods without the code blocks and link to the policy optimization docs for people who want more information
Signed-off-by: subhankar-ghosh <subhankar2321@gmail.com>
|
@shehzeen , can you do a pass over the RL docs? |
Signed-off-by: Shehzeen Hussain <shehzeensh@gmail.com>
|
[🤖]: Hi @subhankar-ghosh 👋, We wanted to let you know that a CICD pipeline for this PR just finished successfully. So it might be time to merge this PR or get some approvals. |
Important
The
Update branchbutton must only be pressed in very rare occassions.An outdated branch is never blocking the merge of a PR.
Please reach out to the automation team before pressing that button.
What does this PR do ?
Add magpietts docs
Collection: [Note which collection this PR will affect]
Changelog
Usage
Documentation
GitHub Actions CI
The Jenkins CI system has been replaced by GitHub Actions self-hosted runners.
The GitHub Actions CI will run automatically when the "Run CICD" label is added to the PR.
To re-run CI remove and add the label again.
To run CI on an untrusted fork, a NeMo user with write access must first click "Approve and run".
Before your PR is "Ready for review"
Pre checks:
PR Type:
If you haven't finished some of the above items you can still open "Draft" PR.
Who can review?
Anyone in the community is free to review the PR once the checks have passed.
Contributor guidelines contains specific people who can review PRs to various areas.
Additional Information