Wav2vec2 Large Xlsr Arabic

🚀 Wav2Vec2-Large-XLSR-53-阿拉伯语模型

本项目是基于Common Voice阿拉伯语数据集，对facebook/wav2vec2-large-xlsr-53模型进行微调得到的语音识别模型。使用该模型时，请确保输入的语音采样率为16kHz。

模型信息

🚀 快速开始

本模型可直接使用（无需语言模型），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

基础用法

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])

高级用法

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"])))

🔧 评估

在Common Voice阿拉伯语测试集上对模型进行评估，代码如下：

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"])))

测试结果：字错误率（WER）为46.77%

📚 训练

训练使用了Common Voice数据集的train和validation子集。

训练脚本可在此处找到。

📄 许可证

本模型使用Apache-2.0许可证。