Wav2vec2 Large Xlsr Mr 2

🚀 Wav2Vec2-Large-XLSR-53-馬拉地語

本模型基於 facebook/wav2vec2-large-xlsr-53，使用 InterSpeech 2021 馬拉地語 數據集的一部分進行微調。使用此模型時，請確保語音輸入的採樣率為 16kHz。

🔍 模型信息

🚀 快速開始

本模型可直接使用（無需語言模型），假設你有一個包含馬拉地語 sentence 和 path 字段的數據集：

💻 使用示例

基礎用法

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

# test_dataset = #TODO: WRITE YOUR CODE TO LOAD THE TEST DATASET. For sample see the Colab link in Training Section.

processor = Wav2Vec2Processor.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr-2")
model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr-2")

resampler = torchaudio.transforms.Resample(8_000, 16_000) # The original data was with 8,000 sampling rate. You can change it according to your input.

# 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])

評估

可以在 InterSpeech-2021 馬拉地語數據的測試集上對模型進行評估：

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

# test_dataset = #TODO: WRITE YOUR CODE TO LOAD THE TEST DATASET. For sample see the Colab link in Training Section.

wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr-2")
model = Wav2Vec2ForCTC.from_pretrained("gchhablani/wav2vec2-large-xlsr-mr-2")
model.to("cuda")

chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\'\�]'
resampler = torchaudio.transforms.Resample(8_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"])))

測試結果：19.98 % （使用測試集中的 555 個示例進行評估）

在 OpenSLR74 數據 10% 上的測試結果：64.64 %

訓練

使用了 InterSpeech 馬拉地語數據集的 5000 個示例進行訓練。訓練使用的 Colab 筆記本可在 此處 找到。

📄 許可證

本項目採用 Apache-2.0 許可證。