Unispeech 1350 En 168 Es Ft 1h

🚀 UniSpeech-Large-plus Spanish

A pre - trained speech model fine - tuned on Spanish phonemes, leveraging Microsoft's UniSpeech technology for accurate automatic speech recognition.

🚀 Quick Start

This model is a large - scale model pre - trained on 16kHz sampled speech audio and phonetic labels, and then fine - tuned on 1 hour of Spanish phonemes. When using the model, ensure that your speech input is also sampled at 16kHz and your text is converted into a sequence of phonemes.

The original Microsoft's UniSpeech is a unified pre - training approach for learning speech representations with both unlabeled and labeled data.

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.

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

✨ Features

• Trained on 16kHz sampled speech audio and phonetic labels.
• Fine - tuned on 1 hour of Spanish phonemes.
• Suitable for automatic speech recognition tasks in Spanish.

📦 Installation

No specific installation steps are provided in the original document.

💻 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-168-es-ft-1h"

sample = next(iter(load_dataset("common_voice", "es", 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:
# b j e n i k e ɾ ɾ e ɣ a l o a s a β ɾ i ɾ p ɾ i m e ɾ o'
# for: Bien . ¿ y qué regalo vas a abrir primero ?

📚 Documentation

This is an speech model that has been fine - tuned on phoneme classification.

🔧 Technical Details

The model is based on Microsoft's UniSpeech, which uses a unified pre - training approach. It combines supervised phonetic CTC learning and phonetically - aware contrastive self - supervised learning in a multi - task learning manner. This allows the model to capture information more correlated with phonetic structures and improve generalization across languages and domains.

📄 License

The official license can be found here

📊 Official Results

See UniSpeeech-L^{+} - es:

👥 Contribution

The model was contributed by cywang and patrickvonplaten.