From 72b768e0be75d36dd504e61dd1b4cbe0901c765a Mon Sep 17 00:00:00 2001 From: Manan Shah <52329525+Manan17@users.noreply.github.com> Date: Thu, 19 Mar 2026 03:52:07 -0500 Subject: [PATCH] Fixing Qwen3.5 bug and adding Outetts dependencies (#4459) * 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 --- studio/backend/requirements/extras.txt | 5 +++-- studio/backend/utils/models/model_config.py | 5 ++++- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/studio/backend/requirements/extras.txt b/studio/backend/requirements/extras.txt index 170b1c9ec8..d783975a4f 100644 --- a/studio/backend/requirements/extras.txt +++ b/studio/backend/requirements/extras.txt @@ -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 diff --git a/studio/backend/utils/models/model_config.py b/studio/backend/utils/models/model_config.py index aaf15994be..13f1b5febf 100644 --- a/studio/backend/utils/models/model_config.py +++ b/studio/backend/utils/models/model_config.py @@ -630,7 +630,10 @@ _AUDIO_TOKEN_PATTERNS = { "whisper": lambda tokens: "<|startoftranscript|>" in tokens, "audio_vlm": lambda tokens: "" 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(" 10000, }