---
base_model: XiaomiMiMo/MiMo-Audio-7B-Instruct
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:XiaomiMiMo/MiMo-Audio-7B-Instruct
- lora
- transformers
new_version: mrfakename/EmoAct-MiMo-v1.1
---

Audio samples (thanks to Christoph from LAION for generating them):


<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/62e54f0eae9d3f10acb95cb9/F_U1U9-6ny_5tKKaI9tFZ.wav"></audio>

<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/62e54f0eae9d3f10acb95cb9/SuCNcoHqgZ7TNa6EvpAGL.wav"></audio>

Very early checkpoint, but it's a good model/finetune.

Base model: MiMo Audio

Prompt format:

```
Emotion: <emotion>
Text: <text>
```

Example:

```
Emotion: intense anger, rage, fury, hatred, and annoyance, speaking without any accent
Text: You know what? I'm done. I'm done with your excuses. (sharp exhale) Every single time, it's the same, and I actually believed you'd change. (voice cracks slightly) God, I'm such an idiot for trusting you again.
```

Training code (private): https://github.com/fakerybakery/mimo2

Voice cloning is not supported yet, coming soon.

Questions/feedback: DM `realmrfakename` on discord