---
license: apache-2.0
pipeline_tag: text-to-speech
tags:
- model_hub_mixin
- pytorch_model_hub_mixin
language:
- sw
base_model:
- sesame/csm-1b
---
# Swa-CSM-1B

**Swa-CSM-1B** is the best open-source Swahili text-to-speech model, fine-tuned from [Sesame's CSM-1B](https://huggingface.co/sesame/csm-1b) for high-quality Swahili speech generation. This model powers [Soga](https://nadhari.ai/soga), a Swahili AI voice assistant.

Developed by [Nadhari AI Lab](https://nadhari.ai) .

## Model Details

- **Base Model:** [sesame/csm-1b](https://huggingface.co/sesame/csm-1b)
- **Language:** Swahili (sw)
- **Task:** Text-to-Speech
- **Architecture:** Llama backbone with Mimi audio decoder (RVQ codes)


## Usage

### Basic Generation

```python
import torch
from transformers import CsmForConditionalGeneration, AutoProcessor

model_id = "Nadhari/swa-csm-1b"
device = "cuda" if torch.cuda.is_available() else "cpu"

processor = AutoProcessor.from_pretrained(model_id)
model = CsmForConditionalGeneration.from_pretrained(model_id, device_map=device)

# Generate Swahili speech
text = "[0]Mambo vipi?."
inputs = processor(text, add_special_tokens=True).to(device)

audio = model.generate(**inputs, output_audio=True)
processor.save_audio(audio, "swahili_output.wav")
```

### With Conversation Context

For best results, provide conversational context:

```python
conversation = [
    {"role": "0", "content": [{"type": "text", "text": "Habari yako?"}]},
]
inputs = processor.apply_chat_template(
    conversation,
    tokenize=True,
    return_dict=True,
).to(device)

audio = model.generate(**inputs, output_audio=True)
processor.save_audio(audio, "swahili_conversation.wav")
```



## Intended Use

This model is designed for:
- Swahili text-to-speech applications
- Research in African language speech synthesis.

## Limitations

- Optimized for standard Swahili; performance may vary with regional dialects
- Inherited limitations from base CSM-1B model
- Best results achieved with conversational context

## Ethical Considerations

This model should not be used for:
- Impersonation or fraud
- Generating misleading or deceptive content
- Any illegal or harmful activities

By using this model, you agree to use it responsibly and ethically.

## Citation

```bibtex
@misc{swa-csm-1b,
  author = {Nadhari AI Lab},
  title = {Swa-CSM-1B: Swahili Text-to-Speech Model},
  year = {2025},
  publisher = {Hugging Face},
  url = {https://huggingface.co/Nadhari/swa-csm-1b}
}
```

## Acknowledgments

- [Sesame](https://www.sesame.com/) for the base CSM-1B model


## Contact

- **Organization:** [Nadhari AI Lab](https://nadhari.ai)
- **Author:** [Alfaxad](https://nadhari.ai)
- **Email:** [research@nadhari.ai]

---