---
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-f8
  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-f8

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: 0.2402
- Per: 0.2682

## 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    |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
| 17.5845       | 0.7194  | 400   | 4.5602          | 0.9886 |
| 4.3975        | 1.4388  | 800   | 4.0866          | 0.9886 |
| 4.065         | 2.1583  | 1200  | 3.6219          | 0.9886 |
| 3.2226        | 2.8777  | 1600  | 1.5150          | 0.4234 |
| 2.0377        | 3.5971  | 2000  | 0.8497          | 0.3379 |
| 1.5778        | 4.3165  | 2400  | 0.6105          | 0.3031 |
| 1.3497        | 5.0360  | 2800  | 0.4982          | 0.2907 |
| 1.1857        | 5.7554  | 3200  | 0.4353          | 0.2848 |
| 1.1177        | 6.4748  | 3600  | 0.3863          | 0.2798 |
| 1.024         | 7.1942  | 4000  | 0.3520          | 0.2775 |
| 0.97          | 7.9137  | 4400  | 0.3349          | 0.2744 |
| 0.9251        | 8.6331  | 4800  | 0.3245          | 0.2748 |
| 0.8806        | 9.3525  | 5200  | 0.3125          | 0.2740 |
| 0.8425        | 10.0719 | 5600  | 0.3029          | 0.2739 |
| 0.8281        | 10.7914 | 6000  | 0.2969          | 0.2729 |
| 0.8361        | 11.5108 | 6400  | 0.2877          | 0.2716 |
| 0.8199        | 12.2302 | 6800  | 0.2805          | 0.2729 |
| 0.7637        | 12.9496 | 7200  | 0.2859          | 0.2717 |
| 0.7653        | 13.6691 | 7600  | 0.2708          | 0.2701 |
| 0.7716        | 14.3885 | 8000  | 0.2727          | 0.2715 |
| 0.745         | 15.1079 | 8400  | 0.2677          | 0.2719 |
| 0.7443        | 15.8273 | 8800  | 0.2624          | 0.2707 |
| 0.7337        | 16.5468 | 9200  | 0.2588          | 0.2697 |
| 0.7032        | 17.2662 | 9600  | 0.2617          | 0.2700 |
| 0.7023        | 17.9856 | 10000 | 0.2586          | 0.2702 |
| 0.6926        | 18.7050 | 10400 | 0.2560          | 0.2685 |
| 0.7003        | 19.4245 | 10800 | 0.2520          | 0.2692 |
| 0.6975        | 20.1439 | 11200 | 0.2513          | 0.2700 |
| 0.6816        | 20.8633 | 11600 | 0.2476          | 0.2694 |
| 0.6743        | 21.5827 | 12000 | 0.2452          | 0.2692 |
| 0.6784        | 22.3022 | 12400 | 0.2430          | 0.2690 |
| 0.6601        | 23.0216 | 12800 | 0.2443          | 0.2683 |
| 0.6621        | 23.7410 | 13200 | 0.2468          | 0.2686 |
| 0.6597        | 24.4604 | 13600 | 0.2452          | 0.2690 |
| 0.6471        | 25.1799 | 14000 | 0.2469          | 0.2688 |
| 0.6514        | 25.8993 | 14400 | 0.2423          | 0.2682 |
| 0.6134        | 26.6187 | 14800 | 0.2416          | 0.2675 |
| 0.6437        | 27.3381 | 15200 | 0.2423          | 0.2682 |
| 0.6361        | 28.0576 | 15600 | 0.2397          | 0.2683 |
| 0.6168        | 28.7770 | 16000 | 0.2405          | 0.2683 |
| 0.6197        | 29.4964 | 16400 | 0.2402          | 0.2682 |


### Framework versions

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