Wav2vec2 Large Xlsr 53 Estonian

🚀 Wav2Vec2-Large-XLSR-53-Estonian

このモデルは、Common Voice を使用してエストニア語で微調整された facebook/wav2vec2-large-xlsr-53 です。このモデルを使用する際には、音声入力が16kHzでサンプリングされていることを確認してください。

🚀 クイックスタート

モデル情報

モデルの評価結果

• モデル名: XLSR Wav2Vec2 Large 53 - Estonian by Vasilis
• タスク: 音声認識 (Automatic Speech Recognition)
• データセット: Common Voice et
• 評価指標:
  • Test WER: 30.658320
  • Test CER: 5.261490

💻 使用例

基本的な使用法

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

test_dataset = load_dataset("common_voice", "et", split="test[:2%]") #TODO: replace {lang_id} in your language code here. Make sure the code is one of the *ISO codes* of [this](https://huggingface.co/languages) site.

processor = Wav2Vec2Processor.from_pretrained("vasilis/wav2vec2-large-xlsr-53-Estonian") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`
model = Wav2Vec2ForCTC.from_pretrained("vasilis/wav2vec2-large-xlsr-53-Estonian") #TODO: replace {model_id} with your model id. The model id consists of {your_username}/{your_modelname}, *e.g.* `elgeish/wav2vec2-large-xlsr-53-arabic`

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])

高度な使用法

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

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

processor = Wav2Vec2Processor.from_pretrained("vasilis/wav2vec2-large-xlsr-53-Estonian")
model = Wav2Vec2ForCTC.from_pretrained("vasilis/wav2vec2-large-xlsr-53-Estonian")
model.to("cuda")

chars_to_ignore_regex = "[\,\?\.\!\-\;\:\"\“\%\‘\”\�\']"  # TODO: adapt this list to include all special characters you removed from the data

resampler = {
    48_000: torchaudio.transforms.Resample(48_000, 16_000),
    44100: torchaudio.transforms.Resample(44100, 16_000),
    32000: torchaudio.transforms.Resample(32000, 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[sampling_rate](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"])))
print("CER: {:2f}".format(100 * wer.compute(predictions=[" ".join(list(entry)) for entry in result["pred_strings"]], references=[" ".join(list(entry)) for entry in result["sentence"]])))

テスト結果: 30.658320 %

🔧 技術詳細

Common voice の train と validation セットを使用して、20000ステップ（約116エポック）の微調整を行いました。feature extractor (Wav2Vec2FeatureExtractor) と feature projection (Wav2Vec2FeatureProjection) レイヤーは凍結され、encoder レイヤー (Wav2Vec2EncoderStableLayerNorm) のみが微調整されました。

📄 ライセンス

このモデルは Apache-2.0 ライセンスの下で提供されています。