Wav2vec2 Large Xlsr Arabic

🚀 Wav2Vec2-Large-XLSR-53-阿拉伯語模型

本項目是基於Common Voice阿拉伯語數據集，對facebook/wav2vec2-large-xlsr-53模型進行微調得到的語音識別模型。使用該模型時，請確保輸入的語音採樣率為16kHz。

模型信息

🚀 快速開始

本模型可直接使用（無需語言模型），以下是使用示例：

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

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

processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec2-large-xlsr-arabic")
model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec2-large-xlsr-arabic")

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

# Preprocessing the datasets.
# We need to read the audio 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])

💻 使用示例

基礎用法

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

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

processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec2-large-xlsr-arabic")
model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec2-large-xlsr-arabic")

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

# Preprocessing the datasets.
# We need to read the audio 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])

高級用法

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

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

processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec2-large-xlsr-arabic") 
model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec2-large-xlsr-arabic")
model.to("cuda")

chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\؛\\\\\\\\\\\\\\\\—\\\\\\\\\\\\\\\\_get\\\\\\\\\\\\\\\\«\\\\\\\\\\\\\\\\»\\\\\\\\\\\\\\\\ـ\\\\\\\\\\\\\\\\ـ\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\#\\\\\\\\\\\\\\\\،\\\\\\\\\\\\\\\\☭,\\\\\\\\\\\\\\\\؟]'
resampler = torchaudio.transforms.Resample(48_000, 16_000)

# Preprocessing the datasets.
# We need to read the audio 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 audio 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"])))

🔧 評估

在Common Voice阿拉伯語測試集上對模型進行評估，代碼如下：

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

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

processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec2-large-xlsr-arabic") 
model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec2-large-xlsr-arabic")
model.to("cuda")

chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\؛\\\\\\\\\\\\\\\\—\\\\\\\\\\\\\\\\_get\\\\\\\\\\\\\\\\«\\\\\\\\\\\\\\\\»\\\\\\\\\\\\\\\\ـ\\\\\\\\\\\\\\\\ـ\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�\\\\\\\\\\\\\\\\#\\\\\\\\\\\\\\\\،\\\\\\\\\\\\\\\\☭,\\\\\\\\\\\\\\\\؟]'
resampler = torchaudio.transforms.Resample(48_000, 16_000)

# Preprocessing the datasets.
# We need to read the audio 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 audio 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"])))

測試結果：字錯誤率（WER）為46.77%

📚 訓練

訓練使用了Common Voice數據集的train和validation子集。

訓練腳本可在此處找到。

📄 許可證

本模型使用Apache-2.0許可證。