Cnam-LMSSC/EBEN_dummy

Model Card

• Developed by: Cnam-LMSSC
• Model type: EBEN
• Language: French
• License: MIT
• Finetuned dataset: speech_clean subset of Cnam-LMSSC/vibravox
• Samplerate for usage: 16kHz

Training procedure

To reproduce experiment please visit jhauret/vibravox.

Inference script (if you do not want to use the huggingsound library) :

import torch, torchaudio
from vibravox import EBENGenerator
from datasets import load_dataset

audio_16kHz, _ = torch.load("path_to_audio")

cut_audio_16kHz = model.cut_to_valid_length(audio_16kHz)
enhanced_audio_16kHz = model(cut_audio_16kHz)