feat(irodori-tts): add v2 model support with VoiceDesign and chunked DACVAE decode#660
Open
yoshphys wants to merge 4 commits intoBlaizzy:mainfrom
Open
feat(irodori-tts): add v2 model support with VoiceDesign and chunked DACVAE decode#660yoshphys wants to merge 4 commits intoBlaizzy:mainfrom
yoshphys wants to merge 4 commits intoBlaizzy:mainfrom
Conversation
lucasnewman
reviewed
Apr 20, 2026
| # Audio latent dimensions (DACVAE: 128-dim, 48kHz) | ||
| latent_dim: int = 128 | ||
| # Audio latent dimensions (v2: 32-dim Semantic-DACVAE, v1: 128-dim DACVAE) | ||
| latent_dim: int = 32 |
Collaborator
There was a problem hiding this comment.
Will this break the v1 model?
Contributor
Author
There was a problem hiding this comment.
No, it will not.
The default value of latent_dim in IrodoriDiTConfig is used only as a fallback when no config is provided (e.g., in unit tests).
When loading a real model, ModelConfig.from_dict() reads the value from the model's config.json, which explicitly specifies "latent_dim": 128 for v1 and "latent_dim": 32 for v2.
So the default never affects actual model loading.
Collaborator
|
@yoshphys Can you update the README.md for the model with the supported model repo ids, and make sure you run the formatter? |
…DACVAE decode - Support Irodori-TTS v2 (latent_dim=32, Semantic-DACVAE) alongside v1 - Add VoiceDesign caption conditioning (use_caption_condition=True) - Accept instruct kwarg as alias for caption in model.generate() - Use chunked DACVAE decoding (chunk_size=50) to stay within 16GB memory limits Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…e compat - Fix _FakeDACVAE.decode() to accept **kwargs (chunk_size support) - Add _small_irodori_dit_config_voicedesign() and model config helpers - Add TestIrodoriVoiceDesignShapes: forward pass with caption conditioning - Add TestIrodoriVoiceDesignGenerate: generate() with caption and instruct alias Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…fix formatting Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
yoshphys
force-pushed
the
feature/irodori-tts
branch
from
2328e1b to
f56f57c
Compare
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
2 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.
Summary
instructkwarg as alias forcaption(mlx-audio convention)chunk_size=50) to stay within 16 GB memory limits on Apple SiliconUploaded models
Audio comparison
Text: 「その森には、古い言い伝えがありました。月が最も高く昇る夜、静かに耳を澄ませば、風の歌声が聞こえるというのです。私は半信半疑でしたが、その夜、確かに誰かが私を呼ぶ声を聞いたのです。」
Usage
Standard (voice cloning)
VoiceDesign (voice description)
🤖 Generated with Claude Code