0xb1's picture
update model card README.md
477183b
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- speech_commands
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-speech_commands-v0.02
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# wav2vec2-base-finetuned-speech_commands-v0.02
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the speech_commands dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1170
- Accuracy: 0.9759
## 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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.9963 | 1.0 | 663 | 0.7316 | 0.9612 |
| 0.4965 | 2.0 | 1326 | 0.2656 | 0.9672 |
| 0.4306 | 3.0 | 1989 | 0.1630 | 0.9720 |
| 0.2901 | 4.0 | 2652 | 0.1283 | 0.9753 |
| 0.2963 | 5.0 | 3315 | 0.1170 | 0.9759 |
### Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3