đ wav2vec2-xls-r-300m-cs-cv8
This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the Common Voice 8.0 dataset, used for automatic speech recognition.
đ Quick Start
This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the common_voice 8.0 dataset. It achieves the following results on the evaluation set:
- WER: 0.49575384615384616
- CER: 0.13333333333333333
⨠Features
- Tags: automatic - speech - recognition, mozilla - foundation/common_voice_8_0, robust - speech - event, xlsr - fine - tuning - week, hf - asr - leaderboard
- Datasets: common_voice
Model Index
Property |
Details |
Model Name |
Slovak comodoro Wav2Vec2 XLSR 300M CV8 |
Task |
Automatic Speech Recognition |
Datasets |
- Common Voice 8 (mozilla - foundation/common_voice_8_0, args: sk)
- Robust Speech Event - Dev Data (speech - recognition - community - v2/dev_data, args: sk)
- Robust Speech Event - Test Data (speech - recognition - community - v2/eval_data, args: sk)
|
Metrics |
- Common Voice 8: Test WER = 49.6, Test CER = 13.3
- Robust Speech Event - Dev Data: Test WER = 81.7
- Robust Speech Event - Test Data: Test WER = 80.26
|
đģ Usage Examples
Basic Usage
import torch
import torchaudio
from datasets import load_dataset
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
test_dataset = load_dataset("mozilla-foundation/common_voice_8_0", "sk", split="test[:2%]")
processor = Wav2Vec2Processor.from_pretrained("comodoro/wav2vec2-xls-r-300m-sk-cv8")
model = Wav2Vec2ForCTC.from_pretrained("comodoro/wav2vec2-xls-r-300m-sk-cv8")
resampler = torchaudio.transforms.Resample(48_000, 16_000)
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"])
đ Documentation
Evaluation
The model can be evaluated using the attached eval.py
script:
python eval.py --model_id comodoro/wav2vec2-xls-r-300m-sk-cv8 --dataset mozilla-foundation/common_voice_8_0 --split test --config sk
Training and evaluation data
The Common Voice 8.0 train
and validation
datasets were used for training
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 7e - 4
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 20
- total_train_batch_size: 640
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 50
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0
đ License
This model is licensed under the Apache 2.0 license.