Vits Icelandic Rosa Female Monospeaker

🚀 Model Card for Sigurdur/vits_icelandic_rosa_female_monospeaker

This is a text-to-speech model for Icelandic. It is fine-tuned from facebook/mms-tts-isl using the Talrómur dataset, offering a practical solution for Icelandic text-to-speech applications.

🚀 Quick Start

This model is designed for text-to-speech applications in Icelandic. Here's a basic example of how to use it:

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

Save Output to File

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

View in Jupyter Notebook

from IPython.display import Audio

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

✨ Features

• Icelandic Support: Specifically fine-tuned for Icelandic text-to-speech, providing high-quality voice output for the Icelandic language.
• Based on VITS: Built on the VITS architecture, ensuring efficient and accurate speech synthesis.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

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

Advanced Usage

The basic usage example covers most common scenarios. There is no additional advanced usage information provided in the original document.

📚 Documentation

Model Details

• Developed by: Sigurdur Haukur Birgisson
• Model type: VITS
• Language(s) (NLP): Icelandic, isl
• License: [More Information Needed]
• Finetuned from model: facebook/mms-tts-isl

Uses

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

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

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

Training Data

[More Information Needed]

Training Hyperparameters

• Training regime: fp16

Evaluation

[More Information Needed]

Model Examination

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Technical Specifications

[More Information Needed]

Citation

[More Information Needed]

Glossary

[More Information Needed]

More Information

[More Information Needed]

📄 License

[More Information Needed]

Model Card Authors

Sigurdur Haukur Birgisson

Model Card Contact

Feel free to contact me through Linkedin: Sigurdur Haukur Birgisson