YAML Metadata
Error:
"datasets[0]" with value "https://arabicspeech.org/" is not valid. If possible, use a dataset id from https://hf.co/datasets.
YAML Metadata
Error:
"model-index[0].results[0].dataset.type" with value "arabicspeech.org MGB-3" fails to match the required pattern: /^(?:[\w-]+\/)?[\w-.]+$/
Wav2Vec2-Large-XLSR-53-Egyptian-Arabic
Fine-tuned facebook/wav2vec2-large-xlsr-53 in Egyptian using the arabicspeech.org MGB-3 When using this model, make sure that your speech input is sampled at 16kHz.
Usage
The model can be used directly (without a language model) as follows:
import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
test_dataset = load_dataset("common_voice", "ar", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec2-large-xlsr-egyptian")
model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec2-large-xlsr-egyptian")
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = torchaudio.load(batch["path"])
batch["speech"] = resampler(speech_array).squeeze().numpy()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset["speech"][:2], 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)
print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset["sentence"][:2])
Evaluation
The model can be evaluated as follows on the Arabic test data of Common Voice.
import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
test_dataset = load_dataset("common_voice", "ar", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("othrif/wav2vec2-large-xlsr-egyptian")
model = Wav2Vec2ForCTC.from_pretrained("othrif/wav2vec2-large-xlsr-egyptian")
model.to("cuda")
chars_to_ignore_regex = '[\؛\—\_get\«\»\ـ\ـ\,\?\.\!\-\;\:\"\“\%\‘\”\�\#\،\☭,\؟]'
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def speech_file_to_array_fn(batch):
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
speech_array, sampling_rate = torchaudio.load(batch["path"])
batch["speech"] = resampler(speech_array).squeeze().numpy()
return batch
test_dataset = test_dataset.map(speech_file_to_array_fn)
# Preprocessing the datasets.
# We need to read the audio files as arrays
def evaluate(batch):
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["pred_strings"] = processor.batch_decode(pred_ids)
return batch
result = test_dataset.map(evaluate, batched=True, batch_size=8)
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
Test Result: 55.2
Training
The Common Voice train
, validation
datasets were used for training.
The script used for training can be found here
- Downloads last month
- 5,923
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.