Edit model card
YAML Metadata Error: "language" must only contain lowercase characters
YAML Metadata Error: "language" with value "sv-SE" is not valid. It must be an ISO 639-1, 639-2 or 639-3 code (two/three letters), or a special value like "code", "multilingual". If you want to use BCP-47 identifiers, you can specify them in language_bcp47.

wav2vec2-large-xlsr-53-Swedish

Fine-tuned facebook/wav2vec2-large-xlsr-53 in Swedish using the Common Voice

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", "sv-SE", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish")

model = Wav2Vec2ForCTC.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish")

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 Swedish 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", "sv-SE", split="test")

wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish")

model = Wav2Vec2ForCTC.from_pretrained("MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish")

model.to("cuda")

chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'

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):

    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()

    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)

# Preprocessing the datasets.

# We need to read the aduio files as arrays

def evaluate(batch):

    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)

    with torch.no_grad():

        logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits

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

    batch["pred_strings"] = processor.batch_decode(pred_ids)

    return batch

result = test_dataset.map(evaluate, batched=True, batch_size=8)

print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))

Test Result: 41.388337 %

Training

The Common Voice train, validation datasets were used for training.

Downloads last month
5
Hosted inference API
or or
This model can be loaded on the Inference API on-demand.

Dataset used to train MehdiHosseiniMoghadam/wav2vec2-large-xlsr-53-Swedish

Evaluation results