unslothai/unsloth

Request for Notebook to Fine-Tune Qwen TTS (or Alternatives Using Existing Notebooks)

Open

#3,961 创建于 2026年2月2日

在 GitHub 查看
 (0 评论) (0 反应) (0 负责人)Python (64,271 star) (5,658 fork)batch import
feature requestgood first issuehelp wanted

描述

Hi Unsloth team, I'm interested in fine-tuning the new Qwen TTS model using Unsloth for efficient training. Could you please share a sample notebook demonstrating how to fine-tune it with Unsloth? If that's not available yet, is there another way to adapt one of your existing notebooks (e.g., for other multimodal or audio models) to work with Qwen TTS? Thanks for your amazing work on making fine-tuning accessible! Best, supreme-ai

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-2 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
fresh
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
Familiarity with unslothUnderstanding of TTS models
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
40
研究方向
This issue requests a notebook for fine tuning Qwen TTS using Unsloth. The team should consider adapting existing fine tuning notebooks (e.g., for multimodal or audio models) in the repository to support Qwen TTS. Key files to examine are the existing notebook templates and the unsloth library's fine tuning utilities. No linked PRs or comments exist yet, so the scope remains open for exploration.