Downloads · 30 days
62
2% of all-time downloads
indonesian-nlp/wav2vec2-large-xlsr-indonesian-baseline
wav2vec2-large-xlsr-indonesian-baseline is a automatic speech recognition model from indonesian-nlp. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This is the baseline for Wav2Vec2-Large-XLSR-Indonesian, a fine-tuned facebook/wav2vec2-large-xlsr-53 model on the Indonesian Common Voice dataset. It was trained using the default hyperparamer and for 2x30 epochs. Wh…
Downloads · 30 days
62
2% of all-time downloads
All-time downloads
3.7K
Public
Repo size
3.8 GB
Likes
3
Public
Click a slice to open those files.
.bin1.3 GB · 50%
From the Hugging Face model README
This is the baseline for Wav2Vec2-Large-XLSR-Indonesian, a fine-tuned facebook/wav2vec2-large-xlsr-53 model on the Indonesian Common Voice dataset. It was trained using the default hyperparamer and for 2x30 epochs. When using this model, make sure that your speech input is sampled at 16kHz.
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", "id", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("indonesian-nlp/wav2vec2-large-xlsr-indonesian-baseline")
model = Wav2Vec2ForCTC.from_pretrained("indonesian-nlp/wav2vec2-large-xlsr-indonesian-baseline")
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 = test_dataset.map(speech_file_to_array_fn)
inputs = processor(test_dataset[:2]["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)
print("Prediction:", processor.batch_decode(predicted_ids))
print("Reference:", test_dataset[:2]["sentence"])
The model can be evaluated as follows on the Indonesian 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", "id", split="test")
wer = load_metric("wer")
processor = Wav2Vec2Processor.from_pretrained("indonesian-nlp/wav2vec2-large-xlsr-indonesian-baseline")
model = Wav2Vec2ForCTC.from_pretrained("indonesian-nlp/wav2vec2-large-xlsr-indonesian-baseline")
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 = 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: 25.55 %
The Common Voice train, validation, and ... datasets were used for training as well as ... and ... # TODO
The script used for training can be found here (will be available soon)