语言: 英文 数据集:

• 通用语音 指标:
• 词错误率(WER)
• 字符错误率(CER) 标签:
• 音频
• 自动语音识别
• 语音
• XLSR微调周 许可证: Apache-2.0 模型索引:
• 名称: Jonatas Grosman的Wav2Vec2英语模型 结果:
  • 任务: 名称: 语音识别 类型: 自动语音识别 数据集: 名称: 通用语音英语 类型: common_voice 参数: en 指标:
    • 名称: 测试WER 类型: wer 值: 21.53
    • 名称: 测试CER 类型: cer 值: 9.66

针对英语语音识别的微调wav2vec2大型模型

基于facebook/wav2vec2-large在英语上进行了微调，使用了Common Voice 6.1的训练和验证分割。使用此模型时，请确保您的语音输入采样率为16kHz。

此模型的微调得益于OVHcloud慷慨提供的GPU资源 :)

训练脚本可在此处找到: https://github.com/jonatasgrosman/wav2vec2-sprint

使用方法

该模型可以直接使用（无需语言模型）如下...

使用HuggingSound库:

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-english")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]

transcriptions = model.transcribe(audio_paths)

编写自己的推理脚本:

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

LANG_ID = "en"
MODEL_ID = "jonatasgrosman/wav2vec2-large-english"
SAMPLES = 10

test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")

processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)

# 预处理数据集
# 我们需要将音频文件读取为数组
def speech_file_to_array_fn(batch):
    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
    batch["speech"] = speech_array
    batch["sentence"] = batch["sentence"].upper()
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"], 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)
predicted_sentences = processor.batch_decode(predicted_ids)

for i, predicted_sentence in enumerate(predicted_sentences):
    print("-" * 100)
    print("参考:", test_dataset[i]["sentence"])
    print("预测:", predicted_sentence)

评估

可以在Common Voice的英语(en)测试数据上评估模型如下。

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

LANG_ID = "en"
MODEL_ID = "jonatasgrosman/wav2vec2-large-english"
DEVICE = "cuda"

CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞",
                   "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
                   "{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
                   "、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
                   "『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "ʻ", "ˆ"]

test_dataset = load_dataset("common_voice", LANG_ID, split="test")

wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py

chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"

processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
model.to(DEVICE)

# 预处理数据集
# 我们需要将音频文件读取为数组
def speech_file_to_array_fn(batch):
    with warnings.catch_warnings():
        warnings.simplefilter("ignore")
        speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
    batch["speech"] = speech_array
    batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
    return batch

test_dataset = test_dataset.map(speech_file_to_array_fn)

# 预处理数据集
# 我们需要将音频文件读取为数组
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(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).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)

predictions = [x.upper() for x in result["pred_strings"]]
references = [x.upper() for x in result["sentence"]]

print(f"WER: {wer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")

测试结果:

在下表中，我报告了模型的词错误率(WER)和字符错误率(CER)。我还在其他模型上运行了上述评估脚本（2021-06-17）。请注意，下表可能显示与已报告结果不同的结果，这可能是由于使用的其他评估脚本的特定性引起的。

引用

如果您想引用此模型，可以使用以下方式:

@misc{grosman2021wav2vec2-large-english,
  title={针对英语语音识别的微调wav2vec2大型模型},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-english}},
  year={2021}
}