Wav2vec2 Large Xlsr 53 Tamil

🚀 Wav2Vec2-Large-XLSR-53-tamil

本模型基於 facebook/wav2vec2-large-xlsr-53，使用 Common Voice 數據集針對泰米爾語進行了微調。使用該模型時，請確保語音輸入的採樣率為 16kHz。

✨ 主要特性

• 支持泰米爾語的自動語音識別任務。
• 基於預訓練模型進行微調，在泰米爾語語音識別上有一定效果。

📦 安裝指南

文檔未提及安裝步驟，若需使用該模型，可參考 Hugging Face 相關庫的安裝方法。

💻 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", "ta", split="test[:2%]")

processor = Wav2Vec2Processor.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-53-tamil")
model = Wav2Vec2ForCTC.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-53-tamil")

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", "ta", split="test")

wer = load_metric("wer")

processor = Wav2Vec2Processor.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-53-tamil")
model = Wav2Vec2ForCTC.from_pretrained("Rajaram1996/wav2vec2-large-xlsr-53-tamil")

model.to("cuda")
chars_to_ignore_regex = '[\\\\,\\\\?\\\\.\\\\!\\\\-\\\\;\\\\:\\\\"\\\\“]'

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):
    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"])))

📚 詳細文檔

評估指標

本模型在 Common Voice 的泰米爾語測試數據上的評估結果如下： 測試結果：字錯率（WER）為 69.76 %

信息表格

📄 許可證

本模型使用的許可證為 Apache-2.0。