Whisper Large V2 Spanish

🚀 西班牙语版Whisper-large-v2模型

本模型是基于Transformer架构的语音识别模型，在特定数据集上微调了openai/whisper-large-v2模型，在评估集上取得了较好的损失和字错率（WER）指标。

🚀 快速开始

此模型是 openai/whisper-large-v2 在特定数据集上的微调版本。它在评估集上取得了以下结果：

• 损失值：0.1466
• 字错率（WER）：0.0855

✨ 主要特性

• 基于openai/whisper-large-v2模型微调，在特定任务上表现更优。
• 提供了训练超参数和训练结果，方便了解模型训练过程。
• 给出了转录和评估的代码示例，便于使用和验证模型。

📦 安装指南

文档未提供具体安装步骤，可参考openai/whisper-large-v2的安装说明，并确保安装以下框架版本：

• Transformers 4.26.0.dev0
• Pytorch 1.13.1+cu117
• Datasets 2.8.1.dev0
• Tokenizers 0.13.2

💻 使用示例

基础用法

from datasets import load_dataset, Audio
import torch
from transformers import WhisperProcessor, WhisperForConditionalGeneration

# device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# load the model
processor = WhisperProcessor.from_pretrained("clu-ling/whisper-large-v2-spanish")
model = WhisperForConditionalGeneration.from_pretrained("clu-ling/whisper-large-v2-spanish").to(device)
forced_decoder_ids = processor.get_decoder_prompt_ids(language="es", task="transcribe")

# load the dataset
commonvoice_eval = load_dataset("mozilla-foundation/common_voice_11_0", "es", split="validation", streaming=True)
commonvoice_eval = commonvoice_eval.cast_column("audio", Audio(sampling_rate=16000))
sample = next(iter(commonvoice_eval))["audio"]

# features and generate token ids
input_features = processor(sample["array"], sampling_rate=sample["sampling_rate"], return_tensors="pt").input_features
predicted_ids = model.generate(input_features.to(device), forced_decoder_ids=forced_decoder_ids)

# decode
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)

print(transcription)

高级用法

from transformers.models.whisper.english_normalizer import BasicTextNormalizer
from datasets import load_dataset, Audio
import evaluate
import torch
import re
from transformers import WhisperProcessor, WhisperForConditionalGeneration

# device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# metric
wer_metric = evaluate.load("wer")

# model
processor = WhisperProcessor.from_pretrained("clu-ling/whisper-large-v2-spanish")
model = WhisperForConditionalGeneration.from_pretrained("clu-ling/whisper-large-v2-spanish")

# dataset
dataset = load_dataset("mozilla-foundation/common_voice_11_0", "es", split="test", )#cache_dir=args.cache_dir
dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))

#for debuggings: it gets some examples
#dataset = dataset.shard(num_shards=10000, index=0)
#print(dataset)
   
def normalize(batch):
  batch["gold_text"] = whisper_norm(batch['sentence'])
  return batch

def map_wer(batch):
  model.to(device)
  forced_decoder_ids = processor.get_decoder_prompt_ids(language = "es", task = "transcribe")
  inputs = processor(batch["audio"]["array"], sampling_rate=batch["audio"]["sampling_rate"], return_tensors="pt").input_features
  with torch.no_grad():
    generated_ids = model.generate(inputs=inputs.to(device), forced_decoder_ids=forced_decoder_ids)
    transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
  batch["predicted_text"] = whisper_norm(transcription)
  return batch

# process GOLD text
processed_dataset = dataset.map(normalize)
# get predictions
predicted = processed_dataset.map(map_wer)

# word error rate
wer = wer_metric.compute(references=predicted['gold_text'], predictions=predicted['predicted_text'])
wer = round(100 * wer, 2)
print("WER:", wer)

🔧 技术细节

训练超参数

训练过程中使用了以下超参数：

• 学习率：1e-05
• 训练批次大小：16
• 评估批次大小：16
• 随机种子：42
• 优化器：Adam（β1=0.9，β2=0.999，ε=1e-08）
• 学习率调度器类型：线性
• 学习率调度器热身步数：500
• 训练步数：25000
• 混合精度训练：Native AMP

训练结果

📄 许可证

本模型采用Apache-2.0许可证。