Wav2vec2 Large Xlsr 53 English

🚀 用於英語語音識別的微調XLSR - 53大模型

本項目是在英語數據集上對 facebook/wav2vec2-large-xlsr-53 進行微調的成果。使用了 Common Voice 6.1 的訓練集和驗證集進行訓練。使用此模型時，請確保語音輸入的採樣率為 16kHz。

該模型的微調得益於 OVHcloud 慷慨提供的 GPU 計算資源。訓練腳本可在 此處 找到。

📦 模型信息

模型評估結果

💻 使用示例

基礎用法

使用 HuggingSound 庫：

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-english")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]

transcriptions = model.transcribe(audio_paths)

高級用法

編寫自己的推理腳本：

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

LANG_ID = "en"
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-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)

# Preprocessing the datasets.
# We need to read the audio files as arrays
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("Reference:", test_dataset[i]["sentence"])
    print("Prediction:", predicted_sentence)

預測結果示例

🔧 模型評估

評估 mozilla - foundation/common_voice_6_0 測試集

python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-english --dataset mozilla-foundation/common_voice_6_0 --config en --split test

評估 speech - recognition - community - v2/dev_data 開發集

python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-english --dataset speech-recognition-community-v2/dev_data --config en --split validation --chunk_length_s 5.0 --stride_length_s 1.0

📄 引用信息

如果您想引用此模型，可以使用以下 BibTeX 格式：

@misc{grosman2021xlsr53-large-english,
  title={Fine-tuned {XLSR}-53 large model for speech recognition in {E}nglish},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english}},
  year={2021}
}