语言: 英语
数据集:

• librispeech_asr
  标签:
• 音频
• 自动语音识别
  许可证: apache-2.0

Wav2Vec2-Base-100h

这是facebook/wav2vec2-base-100h的一个分支版本

变更与说明

1. 文档更新了可复现的评估方法（如下），适配新版transformers和datasets库。
2. 使用批大小为1以复现结果。
3. 已验证兼容transformers v4.15.0和datasets 1.18.0版本。
4. 可能需要手动安装librosa和jiwer这两个Python包。

评估

以下代码片段展示了如何在LibriSpeech的"clean"和"other"测试集上评估facebook/wav2vec2-base-100h模型。

from datasets import load_dataset  
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor  
import soundfile as sf  
import torch  
from jiwer import wer  

librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")  
# librispeech_eval = load_dataset("librispeech_asr", "other", split="test")  

model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-100h").to("cuda")  
processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-100h")  

def map_to_array(batch):  
    # speech, _ = sf.read(batch["file"])  
    # batch["speech"] = speech  
    batch["speech"] = batch['audio']['array']  
    return batch  

librispeech_eval = librispeech_eval.map(map_to_array)  

def map_to_pred(batch):  
    input_values = processor(batch["speech"], return_tensors="pt", padding="longest").input_values  
    with torch.no_grad():  
        logits = model(input_values.to("cuda")).logits  

    predicted_ids = torch.argmax(logits, dim=-1)  
    transcription = processor.batch_decode(predicted_ids)  
    batch["transcription"] = transcription  
    return batch  

result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["speech"])  

print("WER:", wer(result["text"], result["transcription"]))  

词错误率(WER)结果: