Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- accent-conversion
|
| 7 |
+
- speech
|
| 8 |
+
- conformer
|
| 9 |
+
- flow-matching
|
| 10 |
+
library_name: cosyaccent
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# CosyAccent
|
| 14 |
+
|
| 15 |
+
Model weights for **CosyAccent: Duration-Controllable Accent Normalization Using Source-Synthesis Training Data** (ICASSP 2026).
|
| 16 |
+
|
| 17 |
+
- **Paper:** https://arxiv.org/abs/2602.19166v1
|
| 18 |
+
- **data:** https://huggingface.co/datasets/Piping/L2-LibriTTSR
|
| 19 |
+
- **Code & documentation:** https://github.com/Piping/CosyAccent
|
| 20 |
+
|
| 21 |
+
## Usage
|
| 22 |
+
|
| 23 |
+
See the GitHub repository for full installation and inference instructions.
|
| 24 |
+
|
| 25 |
+
Quick start:
|
| 26 |
+
|
| 27 |
+
```bash
|
| 28 |
+
pip install -r requirements.txt
|
| 29 |
+
python infer_wav.py \
|
| 30 |
+
--source_wav /path/to/source.wav \
|
| 31 |
+
--output_wav outputs/result.wav
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
## Citation
|
| 35 |
+
|
| 36 |
+
```bibtex
|
| 37 |
+
@inproceedings{bai2026cosyaccent,
|
| 38 |
+
title={CosyAccent: Duration-Controllable Accent Normalization Using Source-Synthesis Training Data},
|
| 39 |
+
author={Bai, Qibing and Shi, Shuhao and Wang, Shuai and Ju, Yukai and Wang, Yannan and Li, Haizhou},
|
| 40 |
+
booktitle={ICASSP 2026},
|
| 41 |
+
year={2026}
|
| 42 |
+
}
|
| 43 |
+
```
|