---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
  name: Waynehills-STT-doogie-server
---

<!-- 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. -->

# Waynehills-STT-doogie-server

This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7114
- Wer: 1.0056

## 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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 60

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 92.1483       | 1.01  | 100  | 42.2435         | 1.0    |
| 63.5438       | 2.02  | 200  | 30.3017         | 1.0    |
| 40.1961       | 3.03  | 300  | 16.5376         | 1.0    |
| 17.0478       | 4.04  | 400  | 6.9455          | 1.0    |
| 6.3103        | 5.05  | 500  | 4.9786          | 1.0    |
| 4.8201        | 6.06  | 600  | 4.8737          | 1.0    |
| 4.6806        | 7.07  | 700  | 4.8619          | 1.0    |
| 4.6275        | 8.08  | 800  | 4.8368          | 1.0    |
| 4.6017        | 9.09  | 900  | 4.8350          | 1.0    |
| 4.5535        | 10.1  | 1000 | 4.8050          | 1.0    |
| 4.4901        | 11.11 | 1100 | 4.6832          | 1.0    |
| 3.9919        | 12.12 | 1200 | 3.8253          | 1.0    |
| 2.7548        | 13.13 | 1300 | 2.9664          | 1.1167 |
| 2.0868        | 14.14 | 1400 | 2.6503          | 1.1778 |
| 1.6825        | 15.15 | 1500 | 2.4266          | 1.0278 |
| 1.3986        | 16.16 | 1600 | 2.2006          | 1.0944 |
| 1.1716        | 17.17 | 1700 | 2.1571          | 1.0389 |
| 0.9922        | 18.18 | 1800 | 2.0690          | 1.0333 |
| 0.8654        | 19.19 | 1900 | 1.9874          | 1.0222 |
| 0.7447        | 20.2  | 2000 | 1.9131          | 1.0278 |
| 0.6263        | 21.21 | 2100 | 1.8423          | 1.0111 |
| 0.5429        | 22.22 | 2200 | 1.7591          | 1.0111 |
| 0.4715        | 23.23 | 2300 | 1.7380          | 1.0    |
| 0.4245        | 24.24 | 2400 | 1.7531          | 1.0111 |
| 0.3971        | 25.25 | 2500 | 1.8016          | 1.0    |
| 0.3495        | 26.26 | 2600 | 1.6868          | 0.9944 |
| 0.317         | 27.27 | 2700 | 1.8013          | 1.0    |
| 0.2886        | 28.28 | 2800 | 1.6985          | 1.0056 |
| 0.2597        | 29.29 | 2900 | 1.6931          | 1.0056 |
| 0.2269        | 30.3  | 3000 | 1.6208          | 1.0111 |
| 0.2175        | 31.31 | 3100 | 1.6451          | 1.0    |
| 0.2101        | 32.32 | 3200 | 1.7385          | 1.0056 |
| 0.2033        | 33.33 | 3300 | 1.6909          | 1.0111 |
| 0.184         | 34.34 | 3400 | 1.7458          | 1.0    |
| 0.1812        | 35.35 | 3500 | 1.7152          | 1.0    |
| 0.1582        | 36.36 | 3600 | 1.7101          | 1.0    |
| 0.1556        | 37.37 | 3700 | 1.6729          | 1.0056 |
| 0.1398        | 38.38 | 3800 | 1.6982          | 0.9944 |
| 0.1357        | 39.39 | 3900 | 1.6891          | 1.0167 |
| 0.1261        | 40.4  | 4000 | 1.6817          | 1.0    |
| 0.1226        | 41.41 | 4100 | 1.7411          | 1.0    |
| 0.1217        | 42.42 | 4200 | 1.7909          | 1.0    |
| 0.115         | 43.43 | 4300 | 1.6764          | 1.0    |
| 0.1127        | 44.44 | 4400 | 1.6728          | 0.9944 |
| 0.104         | 45.45 | 4500 | 1.7181          | 1.0056 |
| 0.105         | 46.46 | 4600 | 1.7491          | 1.0    |
| 0.0925        | 47.47 | 4700 | 1.7661          | 1.0056 |
| 0.0942        | 48.48 | 4800 | 1.7376          | 1.0    |
| 0.0943        | 49.49 | 4900 | 1.6908          | 1.0111 |
| 0.0859        | 50.51 | 5000 | 1.7193          | 1.0111 |
| 0.0845        | 51.52 | 5100 | 1.7051          | 1.0    |
| 0.0825        | 52.53 | 5200 | 1.6917          | 1.0    |
| 0.08          | 53.54 | 5300 | 1.7093          | 1.0111 |
| 0.0749        | 54.55 | 5400 | 1.7160          | 1.0111 |
| 0.0731        | 55.56 | 5500 | 1.7215          | 1.0111 |
| 0.0725        | 56.57 | 5600 | 1.7251          | 1.0056 |
| 0.0704        | 57.58 | 5700 | 1.7275          | 1.0056 |
| 0.0734        | 58.59 | 5800 | 1.7119          | 1.0056 |
| 0.0729        | 59.6  | 5900 | 1.7114          | 1.0056 |


### Framework versions

- Transformers 4.12.5
- Pytorch 1.10.0+cu113
- Datasets 1.17.0
- Tokenizers 0.10.3