Chinese Hubert Large

🚀 Chinese Speech Pretrained Model

This is a pre - trained speech model, pretrained on 10k hours of WenetSpeech L subset, offering potential for speech recognition tasks.

🚀 Quick Start

This model is pretrained on 10k hours of the WenetSpeech L subset. For more details, please refer to TencentGameMate/chinese_speech_pretrain.

This model does not come with a tokenizer since it was pretrained solely on audio. To use this model for speech recognition, you need to create a tokenizer and fine - tune the model on labeled text data.

📦 Installation

The required Python package is:

transformers==4.16.2

💻 Usage Examples

Basic Usage

import torch
import torch.nn.functional as F
import soundfile as sf

from transformers import (
    Wav2Vec2FeatureExtractor,
    HubertModel,
)

model_path=""
wav_path=""

feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_path)
model = HubertModel.from_pretrained(model_path)

# for pretrain: Wav2Vec2ForPreTraining
# model = Wav2Vec2ForPreTraining.from_pretrained(model_path)

model = model.to(device)
model = model.half()
model.eval()

wav, sr = sf.read(wav_path)
input_values = feature_extractor(wav, return_tensors="pt").input_values
input_values = input_values.half()
input_values = input_values.to(device)

with torch.no_grad():
    outputs = model(input_values)
    last_hidden_state = outputs.last_hidden_state

📄 License

This project is licensed under the MIT license.