ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fixing Qwen3.5 bug and adding Outetts dependencies (#4459)

Browse source 
* Fixing Qwen3.5 bug and adding Outetts dependencies

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Apply suggestion from @danielhanchen

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
This commit is contained in:
Manan Shah 2026-03-19 03:52:07 -05:00 • committed by GitHub
commit 72b768e0be
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
studio/backend/requirements/extras.txt
View file

@ -26,8 +26,9 @@ omegaconf
einx
pyloudnorm
openai-whisper
# uroman # 4.0 MB - romanization, no imports found
# MeCab # 19.9 MB - Japanese tokenizer, no imports found
uroman # 4.0 MB - used for Outetts.
MeCab # 19.9 MB - used for Outetts.
inflect # number-to-words, required by OuteTTS
loguru
flatten_dict
ffmpy

5
studio/backend/utils/models/model_config.py
View file

@ -630,7 +630,10 @@ _AUDIO_TOKEN_PATTERNS = {
"whisper": lambda tokens: "<|startoftranscript|>" in tokens,
"audio_vlm": lambda tokens: "<audio_soft_token>" in tokens,
"bicodec": lambda tokens: any(t.startswith("<|bicodec_") for t in tokens),
"dac": lambda tokens: "<|audio_start|>" in tokens and "<|audio_end|>" in tokens,
"dac": lambda tokens: "<|audio_start|>" in tokens
and "<|audio_end|>" in tokens
and "<|text_start|>" in tokens
and "<|text_end|>" in tokens,
"snac": lambda tokens: sum(1 for t in tokens if t.startswith("<custom_token_"))
> 10000,
}