Wav2vec2 Large Xlsr Hindi

🚀 印地语XLSR Wav2Vec2大模型53

本项目基于以下数据集，对facebook/wav2vec2-large-xlsr-53模型进行了印地语微调：

• 通用语音数据集
• 印度理工学院马德拉斯分校语音合成数据集
• 海得拉巴印度信息技术学院印度语语音数据集

印度语相关数据集在性别和口音方面分布较为均衡，但通用语音数据集在男性语音上存在偏差。

使用印地语数据集对facebook/wav2vec2-large-xlsr-53模型进行了60个轮次的微调，最终字错误率（WER）达到17.05%。

使用此模型时，请确保输入语音的采样率为16kHz。

🚀 快速开始

本模型可直接使用（无需语言模型），具体步骤如下。

✨ 主要特性

• 基于印地语数据集对预训练模型进行微调，适用于印地语语音识别任务。
• 微调使用的数据集在性别和口音方面有不同的分布特点。

📦 安装指南

文档未提及安装步骤，暂不提供相关内容。

💻 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", "hi", split="test")

processor = Wav2Vec2Processor.from_pretrained("skylord/wav2vec2-large-xlsr-hindi") 
model = Wav2Vec2ForCTC.from_pretrained("skylord/wav2vec2-large-xlsr-hindi") 

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])

高级用法

文档未提及高级用法相关代码，暂不提供相关内容。

📚 详细文档

预测结果

部分优质预测结果

部分较差预测结果

评估

该模型可在以下两个数据集上进行评估：

1. 由20%的印度语相关数据集（Indic、IIITH）和通用语音测试集（CV）创建的自定义数据集：字错误率（WER）为17.xx%。
2. 通用语音印地语测试数据集：字错误率（WER）为56.xx%。

数据集的链接在文档开头已提供。训练集和测试集的CSV文件可通过以下谷歌云端硬盘链接获取： a. 海得拉巴印度信息技术学院数据集 训练集 测试集 b. 印度理工学院马德拉斯分校语音合成数据集 训练集 测试集

请根据本地文件结构更新音频路径。

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

## Load the datasets
test_dataset = load_dataset("common_voice", "hi", split="test") 

indic = load_dataset("csv", data_files= {'train':"/workspace/data/hi2/indic_train_full.csv",
                                        "test": "/workspace/data/hi2/indic_test_full.csv"}, download_mode="force_redownload")
iiith = load_dataset("csv", data_files= {"train": "/workspace/data/hi2/iiit_hi_train.csv", 
                                        "test": "/workspace/data/hi2/iiit_hi_test.csv"}, download_mode="force_redownload")

## Pre-process datasets and concatenate to create test dataset
# Drop columns of common_voice
split = ['train', 'test', 'validation', 'other', 'invalidated']

for sp in split:
    common_voice[sp] = common_voice[sp].remove_columns(['client_id', 'up_votes', 'down_votes', 'age', 'gender', 'accent', 'locale', 'segment']) 
    
common_voice = common_voice.rename_column('path', 'audio_path')
common_voice = common_voice.rename_column('sentence', 'target_text')

train_dataset = datasets.concatenate_datasets([indic['train'], iiith['train'], common_voice['train']])
test_dataset = datasets.concatenate_datasets([indic['test'], iiith['test'], common_voice['test'], common_voice['validation']])

## Load model from HF hub

wer = load_metric("wer")

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

chars_to_ignore_regex = '[\,\?\.\!\-\'\;\:\"\“\%\‘\”\�Utrnle\_]'
unicode_ignore_regex = r'[dceMaWpmFui\xa0\u200d]' # Some unwanted unicode chars
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["target_text"] = re.sub(chars_to_ignore_regex, '', batch["target_text"])
  batch["target_text"] = re.sub(unicode_ignore_regex, '', batch["target_text"])
    
  speech_array, sampling_rate = torchaudio.load(batch["audio_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"])))

自定义数据集测试结果：17.23%

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

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

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

chars_to_ignore_regex = '[\,\?\.\!\-\'\;\:\"\“\%\‘\”\�Utrnle\_]'
unicode_ignore_regex = r'[dceMaWpmFui\xa0\u200d]' # Some unwanted unicode chars
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"]).sub(unicode_ignore_regex, '', batch["sentence"])
  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"])))

通用语音数据集测试结果：56.46%

训练

通用语音数据集的训练集和验证集用于模型训练。

训练脚本和Wandb仪表盘可在此处找到。

🔧 技术细节

文档未提及技术实现细节，暂不提供相关内容。

📄 许可证

本项目使用的许可证为Apache-2.0。