---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: kids_phoneme_sm_model
  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. -->

# kids_phoneme_sm_model

This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4558
- Cer: 0.4079

## 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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Cer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 3.0642        | 0.74  | 500   | 4.4995          | 1.0    |
| 2.8486        | 1.48  | 1000  | 3.8639          | 1.0    |
| 2.7909        | 2.22  | 1500  | 3.4712          | 1.0    |
| 1.5475        | 2.96  | 2000  | 1.0263          | 0.6825 |
| 0.7353        | 3.7   | 2500  | 0.8291          | 0.5760 |
| 0.6036        | 4.44  | 3000  | 0.7387          | 0.5327 |
| 0.5553        | 5.19  | 3500  | 0.7382          | 0.5023 |
| 0.4271        | 5.93  | 4000  | 0.7244          | 0.4991 |
| 0.43          | 6.67  | 4500  | 0.7152          | 0.4805 |
| 0.3925        | 7.41  | 5000  | 0.7210          | 0.4587 |
| 0.3719        | 8.15  | 5500  | 0.7888          | 0.4491 |
| 0.3451        | 8.89  | 6000  | 0.7599          | 0.4433 |
| 0.319         | 9.63  | 6500  | 0.7642          | 0.4508 |
| 0.2638        | 10.37 | 7000  | 0.8490          | 0.4426 |
| 0.3084        | 11.11 | 7500  | 0.9387          | 0.4315 |
| 0.2553        | 11.85 | 8000  | 0.8477          | 0.4287 |
| 0.2537        | 12.59 | 8500  | 0.8261          | 0.4301 |
| 0.2058        | 13.33 | 9000  | 1.1093          | 0.4247 |
| 0.2283        | 14.07 | 9500  | 0.7638          | 0.4230 |
| 0.2043        | 14.81 | 10000 | 1.0104          | 0.4219 |
| 0.1918        | 15.56 | 10500 | 0.9618          | 0.4194 |
| 0.1764        | 16.3  | 11000 | 0.9460          | 0.4226 |
| 0.1677        | 17.04 | 11500 | 0.9750          | 0.4233 |
| 0.1751        | 17.78 | 12000 | 0.9600          | 0.4240 |
| 0.1465        | 18.52 | 12500 | 1.1328          | 0.4172 |
| 0.1239        | 19.26 | 13000 | 1.0746          | 0.4176 |
| 0.1495        | 20.0  | 13500 | 1.2143          | 0.4194 |
| 0.1444        | 20.74 | 14000 | 1.1595          | 0.4219 |
| 0.134         | 21.48 | 14500 | 1.1601          | 0.4201 |
| 0.1343        | 22.22 | 15000 | 1.1730          | 0.4233 |
| 0.1051        | 22.96 | 15500 | 1.1257          | 0.4172 |
| 0.1067        | 23.7  | 16000 | 1.1206          | 0.4190 |
| 0.0959        | 24.44 | 16500 | 1.1539          | 0.4133 |
| 0.1028        | 25.19 | 17000 | 1.2425          | 0.4126 |
| 0.1028        | 25.93 | 17500 | 1.2008          | 0.4144 |
| 0.1052        | 26.67 | 18000 | 1.1974          | 0.4094 |
| 0.0813        | 27.41 | 18500 | 1.0960          | 0.4133 |
| 0.0973        | 28.15 | 19000 | 1.1153          | 0.4101 |
| 0.0783        | 28.89 | 19500 | 1.1596          | 0.4126 |
| 0.0704        | 29.63 | 20000 | 1.1881          | 0.4087 |
| 0.068         | 30.37 | 20500 | 1.2289          | 0.4040 |
| 0.0664        | 31.11 | 21000 | 1.2289          | 0.4079 |
| 0.0747        | 31.85 | 21500 | 1.2642          | 0.4122 |
| 0.0663        | 32.59 | 22000 | 1.3062          | 0.4101 |
| 0.0668        | 33.33 | 22500 | 1.3486          | 0.4101 |
| 0.0592        | 34.07 | 23000 | 1.3346          | 0.4040 |
| 0.0513        | 34.81 | 23500 | 1.2958          | 0.4097 |
| 0.0511        | 35.56 | 24000 | 1.3798          | 0.4108 |
| 0.0557        | 36.3  | 24500 | 1.3521          | 0.4065 |
| 0.049         | 37.04 | 25000 | 1.4192          | 0.4094 |
| 0.0465        | 37.78 | 25500 | 1.4308          | 0.4108 |
| 0.0474        | 38.52 | 26000 | 1.4004          | 0.4058 |
| 0.0428        | 39.26 | 26500 | 1.3988          | 0.4054 |
| 0.0509        | 40.0  | 27000 | 1.4218          | 0.4069 |
| 0.0386        | 40.74 | 27500 | 1.3819          | 0.4104 |
| 0.0426        | 41.48 | 28000 | 1.4681          | 0.4090 |
| 0.0408        | 42.22 | 28500 | 1.4543          | 0.4104 |
| 0.0405        | 42.96 | 29000 | 1.4999          | 0.4108 |
| 0.036         | 43.7  | 29500 | 1.4922          | 0.4072 |
| 0.036         | 44.44 | 30000 | 1.4709          | 0.4087 |
| 0.04          | 45.19 | 30500 | 1.4858          | 0.4094 |
| 0.0343        | 45.93 | 31000 | 1.4606          | 0.4087 |
| 0.0288        | 46.67 | 31500 | 1.4599          | 0.4044 |
| 0.0454        | 47.41 | 32000 | 1.4288          | 0.4087 |
| 0.0322        | 48.15 | 32500 | 1.4589          | 0.4083 |
| 0.0327        | 48.89 | 33000 | 1.4502          | 0.4094 |
| 0.0272        | 49.63 | 33500 | 1.4558          | 0.4079 |


### Framework versions

- Transformers 4.30.1
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3