YAML Metadata
Error:
"language" must only contain lowercase characters
wav2vec2-base-gujarati-demo
Fine-tuned facebook/wav2vec2-large-xlsr-53 in Guj 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
common_voice_train,common_voice_test = load_dataset('csv', data_files={'train': 'train.csv','test': 'test.csv'},error_bad_lines=False,encoding='utf-8',split=['train', 'test']).
processor = Wav2Vec2Processor.from_pretrained("jaimin/wav2vec2-base-gujarati-demo")
model = Wav2Vec2ForCTC.from_pretrained("jaimin/wav2vec2-base-gujarati-demo")
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the aduio 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 = common_voice_test.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).logits
predicted_ids = torch.argmax(logits, dim=-1)
print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset["sentence"][0].lower())
Evaluation
The model can be evaluated as follows on the {language} test data of Common Voice.
import torch
import torchaudio
from datasets import load_dataset, load_metric
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
import re
common_voice_validation = load_dataset('csv', data_files={'test': 'validation.csv'},error_bad_lines=False,encoding='utf-8',split='test')
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("jaimin/wav2vec2-base-gujarati-demo")
model = Wav2Vec2ForCTC.from_pretrained("Amrrs/wav2vec2-base-gujarati-demo")
model.to("cuda")
chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
resampler = torchaudio.transforms.Resample(48_000, 16_000)
# Preprocessing the datasets.
# We need to read the aduio 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 = common_voice_validation.map(speech_file_to_array_fn)
# Preprocessing the datasets.
# We need to read the aduio files as arrays
def evaluate(batch):
inputs = processor(batch["speech"], sampling_rate=16000, return_tensors="pt", padding=True)
with torch.no_grad():
logits = model(inputs.input_values.to("cuda")).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["pred_strings"] = processor.batch_decode(pred_ids)
return batch
result = common_voice_validation.map(evaluate, batched=True, batch_size=8)
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
Test Result: 28.92 %
Training
The Google datasets were used for training.
The script used for training can be found here
- Downloads last month
- 2
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.