wav2vec2-xls-r-300m-cs-250 EU AI Act Compliance Profile

Czech wav2vec2-xls-r-300m-cs-250

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice 8.0 dataset as well as other datasets listed below.

It achieves the following results on the evaluation set:

• Loss: 0.1271
• Wer: 0.1475
• Cer: 0.0329

The eval.py script results using a LM are:

• WER: 0.07274312090176113
• CER: 0.021207369275558875

Model description

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

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

test_dataset = load_dataset("mozilla-foundation/common_voice_8_0", "cs", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("comodoro/wav2vec2-xls-r-300m-cs-250")
model = Wav2Vec2ForCTC.from_pretrained("comodoro/wav2vec2-xls-r-300m-cs-250")

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

# Preprocessing the datasets.
# We need to read the aduio 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[:2]["speech"], 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[:2]["sentence"])

Evaluation

The model can be evaluated using the attached eval.py script

Your obligations as a wav2vec2-xls-r-300m-cs-250 deployer

Track your progress

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

Tags

Languages

Library

Base Model