|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: openai/whisper-large-v3 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: uaspeech-large-finetune-shorter-evals-29-11-8AM |
|
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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/neuronbit-tech/finetune_uaspeech_wandb_shorter_evals_29_11_8AM/runs/j3agl8d1) |
|
# uaspeech-large-finetune-shorter-evals-29-11-8AM |
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2763 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 1500 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.3168 | 0.0828 | 200 | 0.3934 | |
|
| 0.2478 | 0.1242 | 300 | 0.3321 | |
|
| 0.2151 | 0.1656 | 400 | 0.3295 | |
|
| 0.1683 | 0.2070 | 500 | 0.3064 | |
|
| 0.1469 | 0.2483 | 600 | 0.3344 | |
|
| 0.1183 | 0.2897 | 700 | 0.2818 | |
|
| 0.0982 | 0.3311 | 800 | 0.2951 | |
|
| 0.1028 | 0.3725 | 900 | 0.2737 | |
|
| 0.0901 | 0.4139 | 1000 | 0.2723 | |
|
| 0.0724 | 0.4553 | 1100 | 0.2761 | |
|
| 0.0668 | 0.4967 | 1200 | 0.2807 | |
|
| 0.0641 | 0.5381 | 1300 | 0.2699 | |
|
| 0.041 | 0.5795 | 1400 | 0.2727 | |
|
| 0.0438 | 0.6209 | 1500 | 0.2763 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
