Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
High-quality speech synthesis with LoRA fine-tuning on index-tts, enhancing prosody and naturalness for single and multi-speaker voices.
| Date | Stars |
|---|---|
| 2026-07-31 | 312 |
| 2026-08-11 | 329 |
| 2026-08-18 | 334 |
| 2026-08-19 | 334 |
| 2026-08-22 | 335 |
| 2026-08-25 | 335 |
| 2026-09-01 | 336 |
| 2026-09-06 | 337 |
| 2026-09-15 | 338 |
| 2026-09-17 | 337 |
| 2026-09-18 | 339 |
| 2026-09-20 | 340 |
| 2026-09-26 | 339 |
| 2026-09-30 | 339 |
| 2026-10-02 | 339 |
| 2026-10-05 | 339 |
| 2026-10-09 | 340 |
| 2026-10-10 | 339 |
| 2026-10-17 | 340 |
| 2026-10-21 | 341 |
| 2026-10-28 | 342 |
| 2026-10-29 | 341 |
| 2026-10-30 | 340 |
| 2026-10-31 | 341 |
| 2026-11-04 | 341 |
Today
— stars today
This week
-1 stars this week
This month
+2 stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="right">
<details>
<summary >🌐 Language</summary>
<div>
<div align="center">
<a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=en">English</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=zh-CN">简体中文</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=zh-TW">繁體中文</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=ja">日本語</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=ko">한국어</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=hi">हिन्दी</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=th">ไทย</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=fr">Français</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=de">Deutsch</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=es">Español</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=it">Italiano</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=ru">Русский</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=pt">Português</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=nl">Nederlands</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=pl">Polski</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=ar">العربية</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=fa">فارسی</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=tr">Türkçe</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=vi">Tiếng Việt</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=id">Bahasa Indonesia</a>
| <a href="https://openaitx.github.io/view.html?user=asr-pub&project=index-tts-lora&lang=as">অসমীয়া</
</div>
</div>
</details>
</div>
# index-tts-lora
[中文版本](https://github.com/asr-pub/index-tts-lora/blob/main/README_zh.md) | [English Version](https://github.com/asr-pub/index-tts-lora/blob/main/README.md)
This project is based on Bilibili's [index-tts](https://github.com/index-tts/index-tts), providing **LoRA fine-tuning** solutions for both **single-speaker and multi-speaker** setups. It aims to enhance **prosody and naturalness** in high-quality speaker audio synthesis.
### Training & Inference
#### 1. Audio token and speaker condition extraction
```shell
# Extract tokens and speaker conditions
python tools/extract_codec.py --audio_list ${audio_list} --extract_condition
# audio_list format: audio_path + transcript, separated by \t
/path/to/audio.wav 小朋友们，大家好，我是凯叔，今天我们讲一个龟兔赛跑的故事。
```
After extraction, the processed files and `speaker_info.json` will be generated under the `finetune_data/processed_data/` directory. For example:
```json
[
{
"speaker": "kaishu_30min",
"avg_duration": 6.6729,
"sample_num": 270,
"total_duration_in_seconds": 1801.696,
"total_duration_in_minutes": 30.028,
"total_duration_in_hours": 0.500,
"train_jsonl": "/path/to/kaishu_30min/metadata_train.jsonl",
"valid_jsonl": "/path/to/kaishu_30min/metadata_valid.jsonl",
"medoid_condition": "/path/to/kaishu_30min/medoid_condition.npy"
}
]
```
#### 2. Training
``Excerpt of 6,398 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d85a43ce64a7c968, desc:fine-tuning, desc:fine tuning, name:lora