# Load model directly
from transformers import AutoProcessor, AutoModelForAudioClassification
processor = AutoProcessor.from_pretrained("anantoj/wav2vec2-large-xlsr-53-adult-child-cls")
model = AutoModelForAudioClassification.from_pretrained("anantoj/wav2vec2-large-xlsr-53-adult-child-cls", device_map="auto")Quick Links
wav2vec2-xls-r-300m-adult-child-cls
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1755
- Accuracy: 0.9432
- F1: 0.9472
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.368 | 1.0 | 383 | 0.2560 | 0.9072 | 0.9126 |
| 0.2013 | 2.0 | 766 | 0.1959 | 0.9321 | 0.9362 |
| 0.22 | 3.0 | 1149 | 0.1755 | 0.9432 | 0.9472 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.3
- Tokenizers 0.11.0
- Downloads last month
- 20
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="anantoj/wav2vec2-large-xlsr-53-adult-child-cls")