|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: unispeech-sat-base-ft |
|
results: [] |
|
datasets: |
|
- mazkooleg/0-9up_google_speech_commands_augmented_raw |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# unispeech-sat-base-ft |
|
|
|
This model is a fine-tuned version of [microsoft/unispeech-sat-base](https://huggingface.co/microsoft/unispeech-sat-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0123 |
|
- Accuracy: 0.9979 |
|
|
|
## 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: 1e-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 | Accuracy | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:--------:|:---------------:| |
|
| 0.0916 | 1.0 | 8558 | 0.9958 | 0.0174 | |
|
| 0.0592 | 2.0 | 17116 | 0.9979 | 0.0123 | |
|
| 0.0725 | 3.0 | 25674 | 0.9958 | 0.0196 | |
|
| 0.0585 | 4.0 | 34232 | 0.9955 | 0.0213 | |
|
| 0.0472 | 5.0 | 42790 | 0.9958 | 0.0212 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.1 |
|
- Pytorch 1.11.0 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.12.1 |
