Wav2vec 2.0 trained with CORAA Portuguese Dataset
This a the demonstration of a fine-tuned Wav2vec model for Portuguese using the following CORAA dataset
Use this model
from transformers import AutoTokenizer, Wav2Vec2ForCTC
tokenizer = AutoTokenizer.from_pretrained("Edresson/wav2vec2-large-xlsr-coraa-portuguese")
model = Wav2Vec2ForCTC.from_pretrained("Edresson/wav2vec2-large-xlsr-coraa-portuguese")
Results
For the results check the CORAA article
Example test with Common Voice Dataset
dataset = load_dataset("common_voice", "pt", split="test", data_dir="./cv-corpus-6.1-2020-12-11")
resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000)
def map_to_array(batch):
speech, _ = torchaudio.load(batch["path"])
batch["speech"] = resampler.forward(speech.squeeze(0)).numpy()
batch["sampling_rate"] = resampler.new_freq
batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'")
return batch
ds = dataset.map(map_to_array)
result = ds.map(map_to_pred, batched=True, batch_size=1, remove_columns=list(ds.features.keys()))
print(wer.compute(predictions=result["predicted"], references=result["target"]))
- Downloads last month
- 254
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.
Evaluation results
- Test CORAA WER on CORAAself-reported25.260
- Test WER on Common Voice 7 on Common Voice 7self-reported20.080