---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-lv-60-espeak-cv-ft
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f1
  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-lv-60-espeak-cv-ft-custom_vocab-OtherDiacritics-ds-f1

This model is a fine-tuned version of [facebook/wav2vec2-lv-60-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-lv-60-espeak-cv-ft) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2794
- Per: 0.2735

## 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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
- num_epochs: 30
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Per    |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
| 17.3102       | 0.7194  | 400   | 4.6225          | 0.9879 |
| 4.434         | 1.4388  | 800   | 4.0923          | 0.9879 |
| 4.084         | 2.1583  | 1200  | 3.6323          | 0.9879 |
| 3.1602        | 2.8777  | 1600  | 1.5314          | 0.4359 |
| 2.0249        | 3.5971  | 2000  | 0.8636          | 0.3477 |
| 1.5696        | 4.3165  | 2400  | 0.6341          | 0.3097 |
| 1.3452        | 5.0360  | 2800  | 0.4947          | 0.2933 |
| 1.2057        | 5.7554  | 3200  | 0.4280          | 0.2849 |
| 1.101         | 6.4748  | 3600  | 0.3829          | 0.2827 |
| 1.0307        | 7.1942  | 4000  | 0.3695          | 0.2828 |
| 0.9897        | 7.9137  | 4400  | 0.3451          | 0.2802 |
| 0.9344        | 8.6331  | 4800  | 0.3360          | 0.2791 |
| 0.885         | 9.3525  | 5200  | 0.3317          | 0.2789 |
| 0.877         | 10.0719 | 5600  | 0.3268          | 0.2786 |
| 0.843         | 10.7914 | 6000  | 0.3190          | 0.2763 |
| 0.8522        | 11.5108 | 6400  | 0.3174          | 0.2770 |
| 0.7951        | 12.2302 | 6800  | 0.3188          | 0.2777 |
| 0.778         | 12.9496 | 7200  | 0.3056          | 0.2748 |
| 0.7645        | 13.6691 | 7600  | 0.3071          | 0.2757 |
| 0.7648        | 14.3885 | 8000  | 0.3034          | 0.2742 |
| 0.7492        | 15.1079 | 8400  | 0.3003          | 0.2733 |
| 0.7344        | 15.8273 | 8800  | 0.2937          | 0.2728 |
| 0.7402        | 16.5468 | 9200  | 0.2922          | 0.2733 |
| 0.7095        | 17.2662 | 9600  | 0.2886          | 0.2731 |
| 0.7079        | 17.9856 | 10000 | 0.2867          | 0.2743 |
| 0.6851        | 18.7050 | 10400 | 0.2938          | 0.2749 |
| 0.6774        | 19.4245 | 10800 | 0.2920          | 0.2742 |
| 0.6964        | 20.1439 | 11200 | 0.2840          | 0.2739 |
| 0.6753        | 20.8633 | 11600 | 0.2853          | 0.2733 |
| 0.6674        | 21.5827 | 12000 | 0.2870          | 0.2736 |
| 0.6893        | 22.3022 | 12400 | 0.2849          | 0.2735 |
| 0.6749        | 23.0216 | 12800 | 0.2775          | 0.2715 |
| 0.6645        | 23.7410 | 13200 | 0.2811          | 0.2732 |
| 0.6572        | 24.4604 | 13600 | 0.2781          | 0.2729 |
| 0.6555        | 25.1799 | 14000 | 0.2792          | 0.2735 |
| 0.651         | 25.8993 | 14400 | 0.2818          | 0.2727 |
| 0.6411        | 26.6187 | 14800 | 0.2792          | 0.2725 |
| 0.6429        | 27.3381 | 15200 | 0.2813          | 0.2728 |
| 0.6259        | 28.0576 | 15600 | 0.2817          | 0.2732 |
| 0.6489        | 28.7770 | 16000 | 0.2806          | 0.2734 |
| 0.631         | 29.4964 | 16400 | 0.2794          | 0.2735 |


### Framework versions

- Transformers 4.57.6
- Pytorch 2.9.1+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2