---
language:
- ca
licence:
- apache-2.0
tags:
- matcha tts
- speech
- text-to-speech
- multispeaker
- catalan
pipeline_tag: text-to-speech
datasets:
- projecte-aina/festcat_trimmed_denoised
- projecte-aina/openslr-slr69-ca-trimmed-denoised
---

# Matcha-TTS Catalan Multispeaker

## Table of Contents
<details>
<summary>Click to expand</summary>

- [Model description](#model-description)
- [Intended uses and limitations](#intended-uses-and-limitations)
- [How to use](#how-to-use)
- [Limitations and bias](#limitations-and-bias)
- [Training](#training)
- [Evaluation](#evaluation)
- [Additional information](#additional-information)

</details>

## Model description

Matcha-TTS is an encoder-decoder architecture designed for fast acoustic modelling in TTS. The encoder predicts phoneme durations and its mean feature vectors. 
And the decoder is essentially a U-Net inspired by Grad-TTS, that is based on Transformers architecture combined 
with 1D instead of 2D CNNs, making a high reduction on memory consumption and speedy synthesis.

Matcha-TTS is non-autorregressive and is trained using optimal-transport conditional flow matching (OT-CFM). 
This yields an ODE-based decoder capable of high output quality in fewer synthesis steps than models trained using score matching.

## Intended uses and limitations

## How to use
```python
import torch
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM

input_text = "Sovint em trobo pensant en tot allò que"

model_id  = "projecte-aina/FLOR-6.3B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
generator = pipeline(
    "text-generation",
    model=model_id,
    tokenizer=tokenizer,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    device_map="auto",
)
generation = generator(
    input_text,
    do_sample=True,
    top_k=10,
    eos_token_id=tokenizer.eos_token_id,
)

print(f"Result: {generation[0]['generated_text']}")
```

## Limitations and bias
At the time of submission, no measures have been taken to estimate the bias and toxicity embedded in the model. 
However, we are well aware that our models may be biased since the corpora have been collected using crawling techniques 
on multiple web sources. We intend to conduct research in these areas in the future, and if completed, this model card will be updated. 


## Training

### Adaptation


### Training data

The model was trained on 2 Catalan speech datasets

| Dataset             | Language | Hours   |
|---------------------|----------|---------|
| Festcat             | ca       | 22      |
| OpenSLR69           | ca       | 5       |

### Languages

Data comes from two different datasets: festcat and openslr69

### Framework


## Evaluation

### Results

## Citation

If this code contributes to your research, please cite the work:

```
@misc{mehta2024matchatts,
      title={Matcha-TTS: A fast TTS architecture with conditional flow matching}, 
      author={Shivam Mehta and Ruibo Tu and Jonas Beskow and Éva Székely and Gustav Eje Henter},
      year={2024},
      eprint={2309.03199},
      archivePrefix={arXiv},
      primaryClass={eess.AS}
}
```

## Additional information

### Author
The Language Technologies Unit from Barcelona Supercomputing Center.

### Contact
For further information, please send an email to <langtech@bsc.es>.

### Copyright
Copyright(c) 2023 by Language Technologies Unit, Barcelona Supercomputing Center.

### License
[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0)

### Funding
This work was funded by [Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya](https://politiquesdigitals.gencat.cat/ca/inici/index.html#googtrans(ca|en) within the framework of [Projecte AINA](https://politiquesdigitals.gencat.cat/ca/economia/catalonia-ai/aina).

### Disclaimer