Wav2Vec2 Fine-Tuned for Pronunciation Correction

This is a fine-tuned Wav2Vec2 model for phoneme-level pronunciation correction. It analyzes speech and provides transcriptions in phonetic notation.

CER = 0.1

Usage

from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import librosa
import torch

# Load model and processor
model = Wav2Vec2ForCTC.from_pretrained("moxeeeem/wav2vec2-finetuned-pronunciation-correction")
processor = Wav2Vec2Processor.from_pretrained("moxeeeem/wav2vec2-finetuned-pronunciation-correction")

def transcribe_audio(speech, sampling_rate):
    inputs = processor(speech, sampling_rate=sampling_rate, return_tensors="pt")
    with torch.no_grad():
        logits = model(inputs.input_values).logits
    pred_ids = torch.argmax(logits, dim=-1)
    return processor.batch_decode(pred_ids)[0]

speech, sample_rate = librosa.load("example_audio.wav", sr=16000)
transcription = transcribe_audio(speech, sample_rate)
print("Transcription:", transcription) # example: pɪŋɡwɪnz lɪv nɪ ði aɪsi ænɑɹtɪk