---
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