---
license: apache-2.0
tags:
- automatic-speech-recognition
- experiments/data/atcosim_uwb_atcc/train
- generated_from_trainer
metrics:
- wer
model-index:
- name: 0.0ld_0.0ad_0.0attd_0.05fpd_0.075mtp_12mtl_0.0mfp_12mfl_1acc
  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. -->

# 0.0ld_0.0ad_0.0attd_0.05fpd_0.075mtp_12mtl_0.0mfp_12mfl_1acc

This model is a fine-tuned version of [facebook/wav2vec2-large-960h-lv60-self](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self) on the EXPERIMENTS/DATA/ATCOSIM_UWB_ATCC/TRAIN - NA dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4042
- Wer: 0.1049

## 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: 0.0001
- train_batch_size: 24
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 10000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| No log        | 0.63  | 500   | 2.2638          | 0.9359 |
| 2.6089        | 1.27  | 1000  | 0.7277          | 0.2407 |
| 2.6089        | 1.9   | 1500  | 0.5800          | 0.1745 |
| 0.6019        | 2.53  | 2000  | 0.4887          | 0.1514 |
| 0.6019        | 3.17  | 2500  | 0.4666          | 0.1421 |
| 0.4722        | 3.8   | 3000  | 0.4426          | 0.1451 |
| 0.4722        | 4.44  | 3500  | 0.4176          | 0.1248 |
| 0.4278        | 5.07  | 4000  | 0.4365          | 0.1239 |
| 0.4278        | 5.7   | 4500  | 0.3816          | 0.1177 |
| 0.369         | 6.34  | 5000  | 0.4113          | 0.1172 |
| 0.369         | 6.97  | 5500  | 0.3863          | 0.1230 |
| 0.341         | 7.6   | 6000  | 0.3850          | 0.1116 |
| 0.341         | 8.24  | 6500  | 0.4014          | 0.1141 |
| 0.3119        | 8.87  | 7000  | 0.3953          | 0.1078 |
| 0.3119        | 9.51  | 7500  | 0.4018          | 0.1080 |
| 0.3008        | 10.14 | 8000  | 0.3964          | 0.1074 |
| 0.3008        | 10.77 | 8500  | 0.3917          | 0.1078 |
| 0.2741        | 11.41 | 9000  | 0.3961          | 0.1057 |
| 0.2741        | 12.04 | 9500  | 0.3974          | 0.1053 |
| 0.2531        | 12.67 | 10000 | 0.4042          | 0.1049 |


### Framework versions

- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.6.1
- Tokenizers 0.13.2