README.md

---
license: llama3.2
base_model: canopylabs/3b-hi-pretrain-research_release
tags:
- text-to-speech
- hindi
- hinglish
- audio-generation
- fine-tuned
- unsloth
language:
- hi
- en
pipeline_tag: text-generation
---

# Hinglish TTS 3B Model

This is a fine-tuned version of [canopylabs/3b-hi-pretrain-research_release](https://huggingface.co/canopylabs/3b-hi-pretrain-research_release) specialized for Hinglish (Hindi-English mixed) text-to-speech generation.

## Model Details

- **Base Model**: canopylabs/3b-hi-pretrain-research_release
- **Fine-tuning Method**: LoRA with Unsloth (merged)
- **Languages**: Hindi, English, Hinglish
- **Task**: Text-to-Speech via audio token generation
- **Model Size**: ~3B parameters

## Usage

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load model and tokenizer
model_name = "Indus-Labs/v1_saavi_devi"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

# Generate text
prompt = "Hello doston, main aapka dost hun"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1200)
```

## Fine-tuning Details

- **LoRA Rank**: 64
- **LoRA Alpha**: 64
- **Target Modules**: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
- **Training Framework**: Unsloth

## Audio Generation

This model generates audio tokens that need to be decoded using a SNAC (Scalable Neural Audio Codec) model:

```python
from snac import SNAC

# Load SNAC decoder
snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz")

# Process generated tokens to audio codes and decode
# (See full implementation in the original training code)
```

## Limitations

- Requires SNAC model for audio generation
- Optimized for Hinglish content
- May not perform well on pure English or pure Hindi in some cases

## Citation

If you use this model, please cite the original base model:

```bibtex
@misc{canopylabs-3b-hi,
  title={3B Hindi Pretrained Model},
  author={Canopy Labs},
  year={2024},
  url={https://huggingface.co/canopylabs/3b-hi-pretrain-research_release}
}
```