wav2vec2-large-xlsr-latvian-cv EU AI Act Compliance Profile

Wav2Vec2-Large-XLSR-Latvian

Fine-tuned facebook/wav2vec2-large-xlsr-53 on the Latvian Common Voice 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:

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

test_dataset = load_dataset("common_voice", "lv", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("jimregan/wav2vec2-large-xlsr-latvian-cv")
model = Wav2Vec2ForCTC.from_pretrained("jimregan/wav2vec2-large-xlsr-latvian-cv")

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["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 the Latvian test data of Common Voice.

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

test_dataset = load_dataset("common_voice", "lv", split="test")
wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("jimregan/wav2vec2-large-xlsr-latvian-cv")
model = Wav2Vec2ForCTC.from_pretrained("jimregan/wav2vec2-large-xlsr-latvian-c

Your obligations as a wav2vec2-large-xlsr-latvian-cv deployer

Track your progress

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

Tags

Languages

Library

Base Model