EMTTS Pronunciation Control - #15965
Open
paarthneekhara wants to merge 21 commits into
Open
Conversation
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| import pytest | ||
| import torch | ||
|
|
||
| import nemo.collections.tts.parts.utils.tts_dataset_utils as tts_dataset_utils |
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
paarthneekhara
marked this pull request as ready for review
July 27, 2026 16:04
paarthneekhara
changed the title
blisc
reviewed
Jul 28, 2026
Resolve MagpieTTS phoneme-token and multiturn integration conflicts while preserving branch-specific phonemization behavior. Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Collaborator
Author
|
/ok to test b7c7efc |
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Collaborator
Author
|
/ok to test ceca177 |
Contributor
|
[🤖]: Hi @paarthneekhara 👋, 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. |
Signed-off-by: Paarth Neekhara <paarth.n@gmail.com>
Collaborator
Author
|
/ok to test 5c4c683 |
Contributor
|
[🤖]: Hi @paarthneekhara 👋, 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. |
Collaborator
Author
|
/ok to test c4b9be7 |
blisc
reviewed
Aug 7, 2026
Comment on lines
+1
to
8
| numpy>=1.26 | ||
| PyYAML>=6.0 | ||
| safetensors>=0.8.0 | ||
| soundfile>=0.13.1 | ||
| tokenizers | ||
|
|
||
| # Runtime dependencies used by EasyMagpie or the speech-serving endpoint. | ||
| transformers>=5.5.3 |
Collaborator
There was a problem hiding this comment.
Suggested change
| numpy>=1.26 | |
| PyYAML>=6.0 | |
| safetensors>=0.8.0 | |
| soundfile>=0.13.1 | |
| tokenizers | |
| # Runtime dependencies used by EasyMagpie or the speech-serving endpoint. | |
| transformers>=5.5.3 | |
| # Runtime dependencies used by EasyMagpie or the speech-serving endpoint. | |
| numpy>=1.26 | |
| PyYAML>=6.0 | |
| safetensors>=0.8.0 | |
| soundfile>=0.13.1 | |
| tokenizers | |
| transformers>=5.5.3 |
blisc
reviewed
Aug 7, 2026
Comment on lines
+9
to
+11
| # vLLM and vLLM-Omni must use the same major/minor version. | ||
| vllm==0.24.0 | ||
| vllm-omni==0.24.0 |
Collaborator
There was a problem hiding this comment.
Suggested change
| # vLLM and vLLM-Omni must use the same major/minor version. | |
| vllm==0.24.0 | |
| vllm-omni==0.24.0 | |
| vllm==0.24.0 # vLLM and vLLM-Omni must use the same major/minor version. | |
| vllm-omni==0.24.0 # vLLM and vLLM-Omni must use the same major/minor version. |
blisc
reviewed
Aug 7, 2026
| if segment_type == "text": | ||
| token_ids.extend(text_tokenizer.encode(text=segment, tokenizer_name=tokenizer_name)) | ||
| else: | ||
| token_ids.extend(text_phoneme_token_offset + token_id for token_id in phoneme_tokenizer.encode(segment)) |
Collaborator
There was a problem hiding this comment.
What happens if someone passes in "Hello my name is"? What happens if graphemes are passed inside of the phoneme tags?
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pronunciation Control for EMTTS using partially phonemized text input.