<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Sinai Voice Arabic Speech Recognition Model

نموذج صوت سيناء للتعرف على الأصوات العربية الفصحى و تحويلها إلى نصوص

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - AR dataset. It achieves the following results on the evaluation set:

• Loss: 0.2141
• Wer: 0.1808

It achieves the following results on the evaluation set:

• eval_loss = 0.2141
• eval_samples = 10388
• eval_wer = 0.181
• eval_cer = 0.049

Evaluation Commands

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

python eval.py --model_id bakrianoo/sinai-voice-ar-stt --dataset mozilla-foundation/common_voice_8_0 --config ar --split test

Inference Without LM

from transformers import (Wav2Vec2Processor, Wav2Vec2ForCTC)
import torchaudio
import torch

def speech_file_to_array_fn(voice_path, resampling_to=16000):
    speech_array, sampling_rate = torchaudio.load(voice_path)
    resampler = torchaudio.transforms.Resample(sampling_rate, resampling_to)
    
    return resampler(speech_array)[0].numpy(), sampling_rate

# load the model
cp = "bakrianoo/sinai-voice-ar-stt"
processor = Wav2Vec2Processor.from_pretrained(cp)
model = Wav2Vec2ForCTC.from_pretrained(cp)

# recognize the text in a sample sound file
sound_path = './my_voice.mp3'

sample, sr = speech_file_to_array_fn(sound_path)
inputs = processor([sample], sampling_rate=16_000, return_tensors="pt", padding=True)

with torch.no_grad():
    logits = model(inputs.input_values,).logits

predicted_ids = torch.argmax(logits, dim=-1)

print("Prediction:", processor.batch_decode(predicted_ids))

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 32
• eval_batch_size: 10
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 256
• total_eval_batch_size: 80
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.2+cu113
• Datasets 1.18.3
• Tokenizers 0.11.0