Wav2vec2 Xls R 1b German

🚀 Fine-tuned XLS-R 1B model for speech recognition in German

This is a fine - tuned model based on facebook/wav2vec2-xls-r-1b for German speech recognition, which uses multiple datasets for training. It can accurately transcribe German speech when the input is sampled at 16kHz.

🚀 Quick Start

This model is a fine - tuned version of facebook/wav2vec2-xls-r-1b on German. It uses the train and validation splits of Common Voice 8.0, Multilingual TEDx, Multilingual LibriSpeech, and Voxpopuli. When using this model, ensure that your speech input is sampled at 16kHz.

This model has been fine - tuned by the HuggingSound tool, and thanks to the GPU credits generously given by the OVHcloud.

✨ Features

• Language Support: Specialized for German speech recognition.
• Data Sources: Trained on multiple high - quality datasets, including Common Voice 8.0, Multilingual TEDx, Multilingual LibriSpeech, and Voxpopuli.
• Fine - tuning Tool: Fine - tuned using the HuggingSound tool.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

Using the HuggingSound library:

from huggingsound import SpeechRecognitionModel

model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-xls-r-1b-german")
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]

transcriptions = model.transcribe(audio_paths)

Advanced Usage

Writing your own inference script:

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

LANG_ID = "de"
MODEL_ID = "jonatasgrosman/wav2vec2-xls-r-1b-german"
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)

📚 Documentation

Evaluation Commands

1. To evaluate on mozilla-foundation/common_voice_8_0 with split test

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

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

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

Model Information

Results

📄 License

This model is licensed under the Apache - 2.0 license.

📚 Citation

If you want to cite this model you can use this:

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