Iwslt Asr Wav2vec Large 4500h

🚀 Fine-Tune Wav2Vec2 large model for English ASR

This project focuses on fine - tuning the Wav2Vec2 large model for English Automatic Speech Recognition (ASR). It uses multiple datasets for fine - tuning and provides evaluation results.

🚀 Quick Start

You can quickly start using this model by clicking the following link to open it in Google Colab:

✨ Features

• Utilizes multiple high - quality datasets for fine - tuning, including Common Voice, Librispeech ASR, How2, etc.
• Provides evaluation results on different datasets with and without a language model.
• Easy - to - use Python code example for inference.

📦 Installation

The README does not provide specific installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers.file_utils import cached_path, hf_bucket_url
from importlib.machinery import SourceFileLoader
from transformers import Wav2Vec2ProcessorWithLM
from IPython.lib.display import Audio
import torchaudio
import torch

# Load model & processor
model_name = "nguyenvulebinh/iwslt-asr-wav2vec-large-4500h"
model = SourceFileLoader("model", cached_path(hf_bucket_url(model_name,filename="model_handling.py"))).load_module().Wav2Vec2ForCTC.from_pretrained(model_name)
processor = Wav2Vec2ProcessorWithLM.from_pretrained(model_name)

# Load an example audio (16k)
audio, sample_rate = torchaudio.load(cached_path(hf_bucket_url(model_name, filename="tst_2010_sample.wav")))
input_data = processor.feature_extractor(audio[0], sampling_rate=16000, return_tensors='pt')

# Infer
output = model(**input_data)

# Output transcript without LM
print(processor.tokenizer.decode(output.logits.argmax(dim=-1)[0].detach().cpu().numpy()))
# and of course there's teams that have a lot more tada structures and among the best are recent graduates of kindergarten

# Output transcript with LM
print(processor.decode(output.logits.cpu().detach().numpy()[0], beam_width=100).text)
# and of course there are teams that have a lot more ta da structures and among the best are recent graduates of kindergarten

📚 Documentation

Data for fine - tune

Evaluation result

🔧 Technical Details

The README does not provide specific technical details, so this section is skipped.

📄 License

The ASR model parameters are made available for non - commercial use only, under the terms of the Creative Commons Attribution - NonCommercial 4.0 International (CC BY - NC 4.0) license. You can find details at: https://creativecommons.org/licenses/by - nc/4.0/legalcode

📞 Contact

You can contact the author via email: nguyenvulebinh@gmail.com