wav2vec2-large-xlsr-kn EU AI Act Compliance Profile

Wav2Vec2-Large-XLSR-53-Kannada

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Kannada using the OpenSLR SLR79 dataset. When using this model, make sure that your speech input is sampled at 16kHz.

Usage

The model can be used directly (without a language model) as follows, assuming you have a dataset with Kannada sentence and path fields:

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

# test_dataset = #TODO: WRITE YOUR CODE TO LOAD THE TEST DATASET. For a sample, see the Colab link in Training Section.

processor = Wav2Vec2Processor.from_pretrained("amoghsgopadi/wav2vec2-large-xlsr-kn")
model = Wav2Vec2ForCTC.from_pretrained("amoghsgopadi/wav2vec2-large-xlsr-kn")
resampler = torchaudio.transforms.Resample(48_000, 16_000) # The original data was with 48,000 sampling rate. You can change it according to your input.

# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
    speech_array, sampling_rate = torchaudio.load(batch["path"])
    batch["speech"] = resampler(speech_array).squeeze().numpy()
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)

with torch.no_grad():
    logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits

predicted_ids = torch.argmax(logits, dim=-1)

print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset["sentence"][:2])

Evaluation

The model can be evaluated as follows on 10% of the Kannada data on OpenSLR.

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

# test_dataset = #TODO: WRITE YOUR CODE TO LOAD T

Your obligations as a wav2vec2-large-xlsr-kn deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library