---
title: Irodori-TTS-v4.1-Anime
canonical_url: "https://www.modelscope.ai/models/phasefield-audio/Irodori-TTS-v4.1-Anime"
md_url: "https://www.modelscope.ai/models/phasefield-audio/Irodori-TTS-v4.1-Anime.md"
repository: phasefield-audio/Irodori-TTS-v4.1-Anime
last_updated: 2026-09-08
license: mit
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
base_model:
  - Aratako/Irodori-TTS-v4.1-Small
base_model_relation: finetune
parameters: 766.1M
tensor_type:
  - BF16
  - I8
  - F8_E4M3
  - F32
  - I32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 97
stars: 1
---

# Irodori-TTS-v4.1-Anime

> Irodori-TTS-v4.1-Anime - An open-source model by phasefield-audio on ModelScope. Irodori-TTS-v4.1-Anime

phasefield-audio/Irodori-TTS-v4.1-Anime is a 766.1M-parameter text-to-speech model on ModelScope. licensed under mit. derived from Aratako/Irodori-TTS-v4.1-Small.

- **Repository**: phasefield-audio/Irodori-TTS-v4.1-Anime
- **License**: mit
- **Tasks**: text-to-speech
- **Parameters**: 766.1M
- **Base model**: Aratako/Irodori-TTS-v4.1-Small
- **Downloads**: 97
- **Stars**: 1
- **Last updated**: 2026-09-08

Source: https://www.modelscope.ai/models/phasefield-audio/Irodori-TTS-v4.1-Anime

---

# Irodori-TTS-v4.1-Anime

A Japanese text-to-speech model fine-tuned from
[Aratako/Irodori-TTS-v4.1-Small](https://huggingface.co/Aratako/Irodori-TTS-v4.1-Small)
using anime-style speech data.

The base model's annotation pipeline is not publicly documented, so the
fine-tuning data was annotated independently. Consequently, caption
conditioning and emoji controls may behave differently from the base model.

## Checkpoints

The full-precision checkpoint is available at the repository root.

Quantized variants are provided in the following subdirectories:

- `int8-weight-only`
- `int8-dynamic`
- `int4-weight-only`
- `float8-weight-only`
- `float8-dynamic`

For inference and installation instructions, see the
[original Irodori-TTS repository](https://github.com/Aratako/Irodori-TTS).

## License

This model follows the same MIT License and ethical restrictions as the base model.