|
--- |
|
license: apache-2.0 |
|
base_model: nadsoft/hamsa-v0.3-qasr |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: hamsa-qasr-meetings |
|
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. --> |
|
|
|
# hamsa-qasr-meetings |
|
|
|
This model is a fine-tuned version of [nadsoft/hamsa-v0.3-qasr](https://huggingface.co/nadsoft/hamsa-v0.3-qasr) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6818 |
|
- Wer: 51.3480 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 1.9407 | 1.0 | 76 | 1.6946 | 67.4632 | |
|
| 1.114 | 2.0 | 152 | 0.9839 | 52.0527 | |
|
| 0.6002 | 3.0 | 228 | 0.6818 | 51.3480 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
