---
language:
- en
tags:
- text-to-speech
- tts
- kokoro
- styletts2
- indian-english
- fine-tuned
license: apache-2.0
base_model: hexgrad/Kokoro-82M
---

# Kokoro-82M — Indian English Fine-Tune

<p>
  <a href="https://github.com/Jeevav62/tts-finetune-recipes/tree/main/kokoro-recipe">
    <img src="https://img.shields.io/badge/GitHub-Fine--Tuning%20Recipe-181717?style=for-the-badge&logo=github&logoColor=white" alt="GitHub Recipe"/>
  </a>
  <a href="https://huggingface.co/hexgrad/Kokoro-82M">
    <img src="https://img.shields.io/badge/Base%20Model-Kokoro--82M-ff6b00?style=for-the-badge&logo=huggingface&logoColor=white" alt="Base Model"/>
  </a>
  <img src="https://img.shields.io/badge/Language-Indian%20English-blue?style=for-the-badge" alt="Language"/>
</p>

🔗 **Recipe:** [kokoro-recipe](https://github.com/Jeevav62/tts-finetune-recipes/tree/main/kokoro-recipe)


A fine-tuned version of [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) adapted for **Indian-accented English** speech synthesis.

This checkpoint handles Indian-English particulars that the base model struggles with — Indic names and city names, the Indian number system (lakh/crore), common Indian-English abbreviations, and the natural rhythm and accent of Indian English speech.

---

## Files

| File | Description |
|---|---|
| `kokoro_converted.pth` | Fine-tuned model weights (Kokoro inference format) |
| `voicepack.pt` | Speaker style tensor `[510, 1, 256]` — male Indian-English voice |

---

## What it handles well

- **Indian names** — Narayanan, Subramanian, Aravind, Sridhar, Venkatesh, Rajkumar, and similar
- **Indian cities** — Bengaluru, Chennai, Hyderabad, Coimbatore, Tiruchirappalli, Madurai
- **Indian number system** — `Rs.7,25,000` → *"seven lakh twenty five thousand rupees"*, crore expansion
- **Tech acronyms** — DDoS, GPU, IST, MMS, CEO, VRAM, AI/ML, CI/CD
- **Natural Indian-English prosody** — accent and rhythm characteristic of Indian English speakers

---

## Usage

```python
import torch
import numpy as np
import soundfile as sf
from kokoro import KModel, KPipeline

# Load model and voicepack
device = "cuda"  # or "cpu"
model = KModel(
    repo_id="hexgrad/Kokoro-82M",
    config="path/to/config.json",         # Kokoro config.json (from hexgrad/Kokoro-82M)
    model="kokoro_converted.pth"
).to(device).eval()

pipeline = KPipeline(lang_code="b", repo_id="hexgrad/Kokoro-82M", model=model)
voice = torch.load("voicepack.pt", map_location="cpu", weights_only=True)

# Synthesize
text = "Dr. Narayanan from Chennai will present the quarterly report — total revenue was Rs.3,75,000."
gen = pipeline.generate_from_tokens(text, voice=voice, speed=1.0)
audio = np.concatenate([a for _, _, a in gen])
sf.write("output.wav", audio, 24000)
```

**G2P note:** For best results, run text through the same G2P pipeline used during training:
- Language: `en-gb` (British espeak via [misaki](https://github.com/hexgrad/misaki))
- Custom lexicon for Indian names recommended (use the same lexicon at inference as at training)

---

## Training Details

| Detail | Value |
|---|---|
| Base model | hexgrad/Kokoro-82M |
| Architecture | StyleTTS2 / ISTFTNet |
| Training framework | [kokoro-deutsch](https://github.com/semidark/kokoro-deutsch) |
| Dataset | ~1,058 clips, single male Indian-English speaker, ~1.5–2h total |
| Audio spec | 24 kHz mono WAV |
| Stage 1 | Acoustic warmup (decoder, style_encoder, text_aligner, pitch_extractor) |
| Stage 2 | 20 epochs prosody fine-tuning (predictor, predictor_encoder) |
| Key hyperparams | `lambda_F0: 2.0`, `batch_size: 4`, `max_len: 200`, `lr: 5e-5` |
| G2P | misaki `en-gb` + custom Indian-English lexicon |

---

## Credits

- **[hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M)** — Base TTS model (Apache 2.0)
- **[yl4579/StyleTTS2](https://github.com/yl4579/StyleTTS2)** — Underlying architecture (MIT)
- **[semidark/kokoro-deutsch](https://github.com/semidark/kokoro-deutsch)** — Training framework (Apache 2.0)
- **[hexgrad/misaki](https://github.com/hexgrad/misaki)** — G2P engine (Apache 2.0)

---

## License

Apache 2.0 — same as the base Kokoro-82M model.