You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Ekodi Bambara TTS

Fine-tuned MMS-TTS model for Bambara (Bamanankan) text-to-speech.

Usage

from transformers import VitsModel, AutoTokenizer
import torch

model = VitsModel.from_pretrained("ynnov/ekodi-bambara-tts")
tokenizer = AutoTokenizer.from_pretrained("ynnov/ekodi-bambara-tts")

text = "I ni ce"  # Hello in Bambara
inputs = tokenizer(text, return_tensors="pt")
with torch.no_grad():
    output = model(**inputs)
waveform = output.waveform[0].numpy()
# waveform is 16kHz float32 audio

Base model

facebook/mms-tts-bam (Meta MMS-TTS, VITS architecture)

Training data

OumarDicko/Bambara_AudioSynthetique_42K_V3
Custom Bambara voice recordings

Project

GitHub: https://github.com/adiarra14/ekodi

Downloads last month: 34

Safetensors

Model size

36.3M params

Tensor type

F32