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")
Downloads last month
9
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Model tree for Arch10/speecht5_tts_voxpopuli_lt

Finetuned
(913)
this model

Dataset used to train Arch10/speecht5_tts_voxpopuli_lt