---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-E10_freq_speed2
  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. -->

# wav2vec2-E10_freq_speed2

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: 1.1541
- Cer: 24.7591

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 44.6688       | 0.1289 | 200  | 5.3220          | 100.0   |
| 5.0381        | 0.2579 | 400  | 4.6642          | 100.0   |
| 4.8478        | 0.3868 | 600  | 4.6375          | 100.0   |
| 4.835         | 0.5158 | 800  | 4.6517          | 100.0   |
| 4.7158        | 0.6447 | 1000 | 4.6317          | 100.0   |
| 4.48          | 0.7737 | 1200 | 4.2848          | 99.9354 |
| 3.5034        | 0.9026 | 1400 | 2.8766          | 51.6627 |
| 2.7033        | 1.0316 | 1600 | 2.4780          | 45.2644 |
| 2.3513        | 1.1605 | 1800 | 2.2651          | 42.3913 |
| 2.0186        | 1.2895 | 2000 | 1.9799          | 36.8096 |
| 1.8504        | 1.4184 | 2200 | 1.9017          | 35.7873 |
| 1.6456        | 1.5474 | 2400 | 1.6934          | 32.8555 |
| 1.5546        | 1.6763 | 2600 | 1.5812          | 31.0576 |
| 1.4543        | 1.8053 | 2800 | 1.4790          | 29.9354 |
| 1.3236        | 1.9342 | 3000 | 1.4232          | 29.2949 |
| 1.2239        | 2.0632 | 3200 | 1.3445          | 27.3678 |
| 1.0797        | 2.1921 | 3400 | 1.2819          | 26.4219 |
| 1.0512        | 2.3211 | 3600 | 1.2911          | 27.0564 |
| 0.9936        | 2.4500 | 3800 | 1.1997          | 25.4994 |
| 0.9784        | 2.5790 | 4000 | 1.2025          | 25.6522 |
| 0.9561        | 2.7079 | 4200 | 1.1842          | 24.8179 |
| 0.9128        | 2.8369 | 4400 | 1.1630          | 24.8237 |
| 0.886         | 2.9658 | 4600 | 1.1541          | 24.7591 |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3