Unispeech 1350 En 353 Fr Ft 1h

🚀 UniSpeech-Large-plus FRENCH

Microsoft's UniSpeech is a large model pretrained on 16kHz sampled speech audio and phonetic labels, and fine - tuned on 1h of French phonemes. It's designed for automatic speech recognition tasks.

🚀 Quick Start

This model is based on Microsoft's UniSpeech. When using the model, ensure that your speech input is sampled at 16kHz and your text is converted into a sequence of phonemes.

✨ Features

• The model is pretrained on 16kHz sampled speech audio and phonetic labels and fine - tuned on French phonemes.
• It can capture information more correlated with phonetic structures and improve generalization across languages and domains.

📚 Documentation

Paper

UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data

Authors

Chengyi Wang, Yu Wu, Yao Qian, Kenichi Kumatani, Shujie Liu, Furu Wei, Michael Zeng, Xuedong Huang

Abstract

In this paper, we propose a unified pre - training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically - aware contrastive self - supervised learning are conducted in a multi - task learning manner. The resultant representations can capture information more correlated with phonetic structures and improve the generalization across languages and domains. We evaluate the effectiveness of UniSpeech for cross - lingual representation learning on public CommonVoice corpus. The results show that UniSpeech outperforms self - supervised pretraining and supervised transfer learning for speech recognition by a maximum of 13.4% and 17.8% relative phone error rate reductions respectively (averaged over all testing languages). The transferability of UniSpeech is also demonstrated on a domain - shift speech recognition task, i.e., a relative word error rate reduction of 6% against the previous approach.

Original Model

The original model can be found under https://github.com/microsoft/UniSpeech/tree/main/UniSpeech.

💻 Usage Examples

Basic Usage

import torch
from datasets import load_dataset
from transformers import AutoModelForCTC, AutoProcessor
import torchaudio.functional as F

model_id = "microsoft/unispeech-1350-en-353-fr-ft-1h"

sample = next(iter(load_dataset("common_voice", "fr", split="test", streaming=True)))
resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy()

model = AutoModelForCTC.from_pretrained(model_id)
processor = AutoProcessor.from_pretrained(model_id)

input_values = processor(resampled_audio, return_tensors="pt").input_values

with torch.no_grad():
    logits = model(input_values).logits

prediction_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(prediction_ids)
# gives -> 'œ̃ v ʁ ɛ t ʁ a v a j ɛ̃ t e ʁ ɛ s ɑ̃ v a ɑ̃ f ɛ̃ ɛ t ʁ ə m ə n e s y ʁ s ə s y ʒ ɛ'
# for 'Un vrai travail intéressant va, enfin, être mené sur ce sujet.'

📄 License

The official license can be found here

📦 Additional Information

Contribution

The model was contributed by cywang and patrickvonplaten.

Official Results

See UniSpeeech - L^{+} - fr: