wav2vec2 large xlsr 53 dutch

提供商jonatasgrosman
分类automatic-speech-recognition
许可证apache-2.0
下载量2.0K
星标0

简介

这是一个基于 Facebook wav2vec 2.0 架构并经过大规模跨语言预训练(XLSR-53)的荷兰语语音识别模型。它专注于将荷兰语语音高效转化为文本,适合需要处理荷兰语语音数据的开发者。由于采用了自监督学习预训练,该模型在小规模标注数据集上也能表现出较强的泛化能力。对于习惯使用 Hugging Face 生态的用户,可以通过 Transformers 库快速部署,上手难度低,是构建荷兰语语音转文字(STT)应用或语音分析工具的理想选择。

核心亮点

  • 专为荷兰语优化,语音识别精度高
  • 基于 XLSR-53 预训练,泛化能力强
  • 兼容 Hugging Face,部署调用极其便捷
  • Apache-2.0 协议,商业使用灵活无压力

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("jonatasgrosman/wav2vec2-large-xlsr-53-dutch")
tokenizer = AutoTokenizer.from_pretrained("jonatasgrosman/wav2vec2-large-xlsr-53-dutch")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引:在下载前,请先通过如下命令安装 huggingface_hub:

操作指引
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库
huggingface-cli download jonatasgrosman/wav2vec2-large-xlsr-53-dutch

下载单个文件到指定本地文件夹(以下载 config.json 到当前路径下 ./dir 目录为例)

下载单个文件到指定本地文件夹(以下载 config.json 到当前路径下 ./dir 目录为例)
huggingface-cli download jonatasgrosman/wav2vec2-large-xlsr-53-dutch config.json --local-dir ./dir

更多命令行下载选项,可参见官方文档

SDK 下载

SDK 下载
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('jonatasgrosman/wav2vec2-large-xlsr-53-dutch')

Git 下载

请确保 lfs 已经被正确安装

Git 下载
git lfs install
git clone https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-dutch

如果您希望跳过 lfs 大文件下载,可以使用如下命令

跳过 LFS
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-dutch

模型文件托管在 Hugging Face Hub,使用 HF CLI / SDK / Git 直接下载,不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers
pip install -U transformers torch

模型加载和推理

模型加载和推理
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('jonatasgrosman/wav2vec2-large-xlsr-53-dutch')
tokenizer = AutoTokenizer.from_pretrained('jonatasgrosman/wav2vec2-large-xlsr-53-dutch')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引:在下载前,请先通过如下命令安装 ModelScope:

操作指引
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库
modelscope download --model jonatasgrosman/wav2vec2-large-xlsr-53-dutch

下载单个文件到指定本地文件夹(以下载 README.md 到当前路径下 dir 目录为例)

下载单个文件到指定本地文件夹(以下载 README.md 到当前路径下 dir 目录为例)
modelscope download --model jonatasgrosman/wav2vec2-large-xlsr-53-dutch README.md --local_dir ./dir

更多更丰富的命令行下载选项,可参见具体文档

SDK 下载

SDK 下载
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('jonatasgrosman/wav2vec2-large-xlsr-53-dutch')

Git 下载

请确保 lfs 已经被正确安装

Git 下载
git lfs install
git clone https://www.modelscope.cn/jonatasgrosman/wav2vec2-large-xlsr-53-dutch.git

如果您希望跳过 lfs 大文件下载,可以使用如下命令

跳过 LFS
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/jonatasgrosman/wav2vec2-large-xlsr-53-dutch.git

ModelScope 模型页直接下载模型文件;无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'jonatasgrosman/wav2vec2-large-xlsr-53-dutch')

完整文档

来源: HuggingFace

---
language: nl
license: apache-2.0
datasets:

  • common_voice

  • mozilla-foundation/common_voice_6_0

metrics:
  • wer

  • cer

tags:
  • audio

  • automatic-speech-recognition

  • hf-asr-leaderboard

  • mozilla-foundation/common_voice_6_0

  • nl

  • robust-speech-event

  • speech

  • xlsr-fine-tuning-week

model-index:
  • name: XLSR Wav2Vec2 Dutch by Jonatas Grosman

results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice nl
type: common_voice
args: nl
metrics:
- name: Test WER
type: wer
value: 15.72
- name: Test CER
type: cer
value: 5.35
- name: Test WER (+LM)
type: wer
value: 12.84
- name: Test CER (+LM)
type: cer
value: 4.64
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Robust Speech Event - Dev Data
type: speech-recognition-community-v2/dev_data
args: nl
metrics:
- name: Dev WER
type: wer
value: 35.79
- name: Dev CER
type: cer
value: 17.67
- name: Dev WER (+LM)
type: wer
value: 31.54
- name: Dev CER (+LM)
type: cer
value: 16.37
---

Fine-tuned XLSR-53 large model for speech recognition in Dutch

Fine-tuned facebook/wav2vec2-large-xlsr-53 on Dutch using the train and validation splits of Common Voice 6.1 and CSS10.
When using this model, make sure that your speech input is sampled at 16kHz.

This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :)

The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint

Usage

The model can be used directly (without a language model) as follows...

Using the HuggingSound library:

python
from huggingsound import SpeechRecognitionModel

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

transcriptions = model.transcribe(audio_paths)

Writing your own inference script:

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

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

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

| Reference | Prediction |
| ------------- | ------------- |
| DE ABORIGINALS ZIJN DE OORSPRONKELIJKE BEWONERS VAN AUSTRALIË. | DE ABBORIGENALS ZIJN DE OORSPRONKELIJKE BEWONERS VAN AUSTRALIË |
| MIJN TOETSENBORD ZIT VOL STOF. | MIJN TOETSENBORD ZIT VOL STOF |
| ZE HAD DE BANK BESCHADIGD MET HAAR SKATEBOARD. | ZE HAD DE BANK BESCHADIGD MET HAAR SCHEETBOORD |
| WAAR LAAT JIJ JE ONDERHOUD DOEN? | WAAR LAAT JIJ HET ONDERHOUD DOEN |
| NA HET LEZEN VAN VELE BEOORDELINGEN HAD ZE EINDELIJK HAAR OOG LATEN VALLEN OP EEN LAPTOP MET EEN QWERTY TOETSENBORD. | NA HET LEZEN VAN VELE BEOORDELINGEN HAD ZE EINDELIJK HAAR OOG LATEN VALLEN OP EEN LAPTOP MET EEN QUERTITOETSEMBORD |
| DE TAMPONS ZIJN OP. | DE TAPONT ZIJN OP |
| MARIJKE KENT OLIVIER NU AL MEER DAN TWEE JAAR. | MAARRIJKEN KENT OLIEVIER NU AL MEER DAN TWEE JAAR |
| HET VOEREN VAN BROOD AAN EENDEN IS EIGENLIJK ONGEZOND VOOR DE BEESTEN. | HET VOEREN VAN BEUROT AAN EINDEN IS EIGENLIJK ONGEZOND VOOR DE BEESTEN |
| PARKET MOET JE STOFZUIGEN, TEGELS MOET JE DWEILEN. | PARKET MOET JE STOF ZUIGEN MAAR TEGELS MOET JE DWEILEN |
| IN ONZE BUURT KENT IEDEREEN ELKAAR. | IN ONZE BUURT KENT IEDEREEN ELKAAR |

Evaluation

1. To evaluate on mozilla-foundation/common_voice_6_0 with split test

bash
python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-dutch --dataset mozilla-foundation/common_voice_6_0 --config nl --split test

2. To evaluate on speech-recognition-community-v2/dev_data

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

Citation

If you want to cite this model you can use this:
bibtex
@misc{grosman2021xlsr53-large-dutch,
  title={Fine-tuned {XLSR}-53 large model for speech recognition in {D}utch},
  author={Grosman, Jonatas},
  howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-dutch}},
  year={2021}
}