Wav2vec2 Large Xlsr Japanese

🚀 Wav2Vec2-Large-XLSR-53-Japanese

This model is fine-tuned from facebook/wav2vec2-large-xlsr-53 on Japanese, aiming to provide high - quality automatic speech recognition for the Japanese language.

🚀 Quick Start

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Japanese using the Common Voice and Japanese speech corpus of Saruwatari-lab, University of Tokyo JSUT. When using this model, make sure that your speech input is sampled at 16kHz.

✨ Features

• Multilingual Adaptability: Based on the large - scale XLSR - 53 model, it has the potential for multilingual adaptation.
• High - Quality Training Data: Trained on the Common Voice dataset and the Japanese speech corpus of Saruwatari - lab, ensuring high - quality performance on Japanese speech recognition.

📦 Installation

To use this model, you need to install the following dependencies:

!pip install mecab-python3
!pip install unidic-lite
!python -m unidic download

💻 Usage Examples

Basic Usage

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

import torch
import torchaudio
import librosa
from datasets import load_dataset
import MeCab
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re

# config
wakati = MeCab.Tagger("-Owakati")
chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\、\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\。\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\．\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\「\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\」\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\…\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\？\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\・]'

# load data, processor and model
test_dataset = load_dataset("common_voice", "ja", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("vumichien/wav2vec2-large-xlsr-japanese")
model = Wav2Vec2ForCTC.from_pretrained("vumichien/wav2vec2-large-xlsr-japanese")
resampler = lambda sr, y: librosa.resample(y.numpy().squeeze(), sr, 16_000)

# Preprocessing the datasets.
def speech_file_to_array_fn(batch):
    batch["sentence"] = wakati.parse(batch["sentence"]).strip()
    batch["sentence"] = re.sub(chars_to_ignore_regex,'', batch["sentence"]).strip()
    speech_array, sampling_rate = torchaudio.load(batch["path"])
    batch["speech"] = resampler(sampling_rate, speech_array).squeeze()
    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])

📚 Documentation

Evaluation

The model can be evaluated as follows on the Japanese test data of Common Voice.

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

#config
wakati = MeCab.Tagger("-Owakati")
chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\、\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\。\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\．\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\「\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\」\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\…\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\？\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\・]'

# load data, processor and model
test_dataset = load_dataset("common_voice", "ja", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("vumichien/wav2vec2-large-xlsr-japanese")
model = Wav2Vec2ForCTC.from_pretrained("vumichien/wav2vec2-large-xlsr-japanese")
model.to("cuda")
resampler = lambda sr, y: librosa.resample(y.numpy().squeeze(), sr, 16_000)

# Preprocessing the datasets.
def speech_file_to_array_fn(batch):
    batch["sentence"] = wakati.parse(batch["sentence"]).strip()
    batch["sentence"] = re.sub(chars_to_ignore_regex,'', batch["sentence"]).strip()
    speech_array, sampling_rate = torchaudio.load(batch["path"])
    batch["speech"] = resampler(sampling_rate, speech_array).squeeze()
    return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)

# evaluate function
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

Training

The Common Voice train, validation datasets and Japanese speech corpus basic5000 datasets were used for training.

📄 License

This project is licensed under the Apache - 2.0 license.