|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- new_dataset |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: wav2vec2-base-finetuned-manthan_base |
|
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-manthan_base |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the new_dataset dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2246 |
|
- Accuracy: 0.9691 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 2.4725 | 0.98 | 12 | 2.4222 | 0.1057 | |
|
| 2.4501 | 1.98 | 24 | 2.2420 | 0.2784 | |
|
| 2.2977 | 2.98 | 36 | 2.0155 | 0.7603 | |
|
| 2.1331 | 3.98 | 48 | 1.8193 | 0.8582 | |
|
| 1.7927 | 4.98 | 60 | 1.6376 | 0.9459 | |
|
| 1.7226 | 5.98 | 72 | 1.4940 | 0.9613 | |
|
| 1.6036 | 6.98 | 84 | 1.3632 | 0.9665 | |
|
| 1.5181 | 7.98 | 96 | 1.2963 | 0.9562 | |
|
| 1.4384 | 8.98 | 108 | 1.2406 | 0.9742 | |
|
| 1.3339 | 9.98 | 120 | 1.2246 | 0.9691 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.19.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 1.14.0 |
|
- Tokenizers 0.12.1 |
|
|
