wav2vec2-large-xlsr-53-sw

Usage

The model can be used directly (without a language model) as follows:

import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor

processor = Wav2Vec2Processor.from_pretrained("alokmatta/wav2vec2-large-xlsr-53-sw")

model = Wav2Vec2ForCTC.from_pretrained("alokmatta/wav2vec2-large-xlsr-53-sw").to("cuda")

resampler = torchaudio.transforms.Resample(48_000, 16_000)

resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000)

def load_file_to_data(file):
    batch = {}
    speech, _ = torchaudio.load(file)
    batch["speech"] = resampler.forward(speech.squeeze(0)).numpy()
    batch["sampling_rate"] = resampler.new_freq
    return batch

def predict(data):
    features = processor(data["speech"], sampling_rate=data["sampling_rate"], padding=True, return_tensors="pt")
    input_values = features.input_values.to("cuda")
    attention_mask = features.attention_mask.to("cuda")
    with torch.no_grad():
        logits = model(input_values, attention_mask=attention_mask).logits
    pred_ids = torch.argmax(logits, dim=-1)
    return processor.batch_decode(pred_ids)

predict(load_file_to_data('./demo.wav'))

Test Result: 40 %

Training