README.md

metadata

license: mit
datasets:
  - facebook/voxpopuli
language:
  - lt
base_model:
  - microsoft/speecht5_tts
pipeline_tag: text-to-speech
tags:
  - code

Model Overview

This model is fine-tuned based on Microsoft’s SpeechT5 for Lithuanian (lt) language text-to-speech (TTS) tasks. The training dataset used is the VoxPopuli dataset.

Model Details

• Base Model: microsoft/speecht5_tts
• Language: Lithuanian (lt)
• License: MIT
• Dataset: VoxPopuli (facebook/voxpopuli)

Usage

from transformers import AutoTokenizer, AutoModelForSpeechT5

tokenizer = AutoTokenizer.from_pretrained("Arch10/speecht5_tts_voxpopuli_lt")
model = AutoModelForSpeechT5.from_pretrained("Arch10/speecht5_tts_voxpopuli_lt")