Cnam-LMSSC/EBEN_reverse_soft_in_ear_microphone
05
<p align="center"> <img src="https://cdn-uploads.huggingface.co/production/uploads/65302a613ecbe51d6a6ddcec/zhB1fh-c0pjlj-Tr4Vpmr.png" style="object-fit:contain; width:280px; height:280px;" > </p>
Model Card
- Developed by: Cnam-LMSSC
- Model: EBEN(M=4,P=4,Q=4) (see publication in IEEE TASLP - arXiv link)
- Language: French
- License: MIT
- Training dataset:
speech_cleansubset of Cnam-LMSSC/vibravox (see VibraVox paper on arXiV) - Testing dataset:
speech_cleansubset of Cnam-LMSSC/vibravox - Samplerate for usage: 16kHz
Overview
This model, trained on Vibravox body conduction sensor data, maps clean speech to body-conducted speech.
Inference script :
import torch, torchaudio
from vibravox.torch_modules.dnn.eben_generator import EBENGenerator
from datasets import load_dataset
model = EBENGenerator.from_pretrained("Cnam-LMSSC/EBEN_reverse_soft_in_ear_microphone")
test_dataset = load_dataset("Cnam-LMSSC/vibravox", "speech_clean", split="test", streaming=True)
audio_48kHz = torch.Tensor(next(iter(test_dataset))["audio.headset_microphone"]["array"])
audio_16kHz = torchaudio.functional.resample(audio_48kHz, orig_freq=48_000, new_freq=16_000)
cut_audio_16kHz = model.cut_to_valid_length(audio_16kHz[None, None, :])
degraded_audio_16kHz, _ = model(cut_audio_16kHz)