README.md

---
library_name: transformers
datasets:
- Sigurdur/talromur-rosa
language:
- is
base_model:
- facebook/mms-tts
pipeline_tag: text-to-speech
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This is a text-to-speach model for Icelandic, it is finetuned from ``facebook/mms-tts-isl`` with the dataset Talrómur (see https://repository.clarin.is/repository/xmlui/handle/20.500.12537/330)



## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

- **Developed by:** Sigurdur Haukur Birgisson
- **Model type:** [VITS](https://huggingface.co/docs/transformers/model_doc/vits)
- **Language(s) (NLP):** Icelandic, isl
- **License:** [More Information Needed]
- **Finetuned from model:** [facebook/mms-tts-isl](https://huggingface.co/facebook/mms-tts-isl)


## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

This model should be used for text-to-speach applications for Icelandic.

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

```py
from transformers import VitsModel, AutoTokenizer
import scipy.io.wavfile as wav
import torch

model = VitsModel.from_pretrained("Sigurdur/vits_icelandic_rosa_female_monospeaker")
tokenizer = AutoTokenizer.from_pretrained("Sigurdur/vits_icelandic_rosa_female_monospeaker")

text = "Góðan daginn! Ég heiti Rósa, ég er talgervill"

inputs = tokenizer(text, return_tensors="pt")
with torch.no_grad():
  output = model(**inputs).waveform

sampling_rate = getattr(sampling_rate, "sampling_rate", 16000)  # Default to 16kHz if not set
if not (0 <= sampling_rate <= 65535):
    raise ValueError(f"Invalid sampling rate: {sampling_rate}")

waveform = output.squeeze().cpu().numpy()  # Remove batch dimension if present
```

To save output to file

```py

wav.write("output.wav", rate=sampling_rate, data=waveform)
```

To view in jupyter notebook

```py
from IPython.display import Audio

# show audio player for "output.wav"
Audio(output, rate=sampling_rate)
```

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]



#### Training Hyperparameters

- **Training regime:** fp16 <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]

## Technical Specifications [optional]

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

[More Information Needed]

#### Hardware

[More Information Needed]

#### Software

[More Information Needed]

## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors

Sigurdur Haukur Birgisson

## Model Card Contact

Feel free to contact me through Linkedin: [Sigurdur Haukur Birgisson](https://www.linkedin.com/in/sigurdur-haukur-birgisson/)