---
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-f4
  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-f4

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: 0.2306
- Per: 0.2634

## 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    |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
| 17.6187       | 0.7194  | 400   | 4.5607          | 0.9856 |
| 4.4013        | 1.4388  | 800   | 4.0856          | 0.9857 |
| 4.0698        | 2.1583  | 1200  | 3.6468          | 0.9857 |
| 3.2539        | 2.8777  | 1600  | 1.5396          | 0.4315 |
| 2.0627        | 3.5971  | 2000  | 0.8367          | 0.3308 |
| 1.5728        | 4.3165  | 2400  | 0.5852          | 0.2961 |
| 1.3596        | 5.0360  | 2800  | 0.4673          | 0.2840 |
| 1.1948        | 5.7554  | 3200  | 0.3952          | 0.2795 |
| 1.1149        | 6.4748  | 3600  | 0.3470          | 0.2751 |
| 1.0246        | 7.1942  | 4000  | 0.3312          | 0.2735 |
| 0.981         | 7.9137  | 4400  | 0.3073          | 0.2724 |
| 0.9367        | 8.6331  | 4800  | 0.2935          | 0.2716 |
| 0.8987        | 9.3525  | 5200  | 0.2827          | 0.2687 |
| 0.8669        | 10.0719 | 5600  | 0.2731          | 0.2687 |
| 0.8606        | 10.7914 | 6000  | 0.2662          | 0.2660 |
| 0.8415        | 11.5108 | 6400  | 0.2667          | 0.2660 |
| 0.81          | 12.2302 | 6800  | 0.2666          | 0.2687 |
| 0.7816        | 12.9496 | 7200  | 0.2575          | 0.2682 |
| 0.7672        | 13.6691 | 7600  | 0.2495          | 0.2647 |
| 0.7615        | 14.3885 | 8000  | 0.2531          | 0.2653 |
| 0.752         | 15.1079 | 8400  | 0.2477          | 0.2649 |
| 0.7634        | 15.8273 | 8800  | 0.2467          | 0.2643 |
| 0.727         | 16.5468 | 9200  | 0.2480          | 0.2642 |
| 0.714         | 17.2662 | 9600  | 0.2441          | 0.2644 |
| 0.7077        | 17.9856 | 10000 | 0.2369          | 0.2651 |
| 0.6914        | 18.7050 | 10400 | 0.2372          | 0.2637 |
| 0.6766        | 19.4245 | 10800 | 0.2376          | 0.2644 |
| 0.6914        | 20.1439 | 11200 | 0.2375          | 0.2640 |
| 0.6766        | 20.8633 | 11600 | 0.2330          | 0.2641 |
| 0.6754        | 21.5827 | 12000 | 0.2359          | 0.2647 |
| 0.6901        | 22.3022 | 12400 | 0.2378          | 0.2652 |
| 0.6657        | 23.0216 | 12800 | 0.2317          | 0.2632 |
| 0.6539        | 23.7410 | 13200 | 0.2327          | 0.2649 |
| 0.6752        | 24.4604 | 13600 | 0.2299          | 0.2636 |
| 0.6584        | 25.1799 | 14000 | 0.2298          | 0.2634 |
| 0.6506        | 25.8993 | 14400 | 0.2339          | 0.2641 |
| 0.6303        | 26.6187 | 14800 | 0.2299          | 0.2634 |
| 0.6488        | 27.3381 | 15200 | 0.2317          | 0.2642 |
| 0.6421        | 28.0576 | 15600 | 0.2305          | 0.2633 |
| 0.6391        | 28.7770 | 16000 | 0.2303          | 0.2640 |
| 0.6251        | 29.4964 | 16400 | 0.2306          | 0.2634 |


### Framework versions

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