用于荷兰语语音识别的Fine-tuned XLS-R 1B模型

使用 Common Voice 8.0 ， Multilingual LibriSpeech 和 Voxpopuli 的训练和验证样本对 facebook/wav2vec2-xls-r-1b 进行荷兰语fine-tuning。在使用此模型时，请确保您的语音输入采样率为16kHz。

该模型是由 HuggingSound 工具进行的fine-tuning，并感谢 OVHcloud 慷慨赠予的GPU积分:)

使用方法

使用 HuggingSound 库：

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-xls-r-1b-dutch")
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 = "nl"
MODEL_ID = "jonatasgrosman/wav2vec2-xls-r-1b-dutch"
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)

评估命令

python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-dutch --dataset mozilla-foundation/common_voice_8_0 --config nl --split test

python eval.py --model_id jonatasgrosman/wav2vec2-xls-r-1b-dutch --dataset speech-recognition-community-v2/dev_data --config nl --split validation --chunk_length_s 5.0 --stride_length_s 1.0

引用

如果您想引用这个模型，可以使用以下内容：

@misc{grosman2021xlsr-1b-dutch,
  title={Fine-tuned {XLS-R} 1{B} model for speech recognition in {D}utch},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-dutch}},
  year={2022}
}