---
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-f6
  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-f6

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: 0.2470
- Per: 0.2700

## 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    |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
| 17.6564       | 0.7194  | 400   | 4.5685          | 0.9888 |
| 4.3982        | 1.4388  | 800   | 4.0889          | 0.9887 |
| 4.078         | 2.1583  | 1200  | 3.6693          | 0.9888 |
| 3.3137        | 2.8777  | 1600  | 1.6025          | 0.4352 |
| 2.0862        | 3.5971  | 2000  | 0.8676          | 0.3350 |
| 1.613         | 4.3165  | 2400  | 0.6230          | 0.3078 |
| 1.3804        | 5.0360  | 2800  | 0.4992          | 0.2936 |
| 1.2312        | 5.7554  | 3200  | 0.4202          | 0.2872 |
| 1.1465        | 6.4748  | 3600  | 0.3793          | 0.2818 |
| 1.0451        | 7.1942  | 4000  | 0.3470          | 0.2783 |
| 0.9853        | 7.9137  | 4400  | 0.3207          | 0.2768 |
| 0.9449        | 8.6331  | 4800  | 0.3132          | 0.2768 |
| 0.8976        | 9.3525  | 5200  | 0.3061          | 0.2752 |
| 0.8768        | 10.0719 | 5600  | 0.2952          | 0.2755 |
| 0.8707        | 10.7914 | 6000  | 0.2927          | 0.2751 |
| 0.854         | 11.5108 | 6400  | 0.2928          | 0.2750 |
| 0.8301        | 12.2302 | 6800  | 0.2845          | 0.2766 |
| 0.8017        | 12.9496 | 7200  | 0.2830          | 0.2726 |
| 0.781         | 13.6691 | 7600  | 0.2815          | 0.2730 |
| 0.7917        | 14.3885 | 8000  | 0.2737          | 0.2723 |
| 0.7449        | 15.1079 | 8400  | 0.2696          | 0.2731 |
| 0.7606        | 15.8273 | 8800  | 0.2674          | 0.2710 |
| 0.7411        | 16.5468 | 9200  | 0.2634          | 0.2710 |
| 0.7137        | 17.2662 | 9600  | 0.2641          | 0.2728 |
| 0.7264        | 17.9856 | 10000 | 0.2567          | 0.2701 |
| 0.7062        | 18.7050 | 10400 | 0.2604          | 0.2708 |
| 0.6896        | 19.4245 | 10800 | 0.2568          | 0.2714 |
| 0.7088        | 20.1439 | 11200 | 0.2566          | 0.2703 |
| 0.6848        | 20.8633 | 11600 | 0.2555          | 0.2699 |
| 0.6857        | 21.5827 | 12000 | 0.2572          | 0.2710 |
| 0.6834        | 22.3022 | 12400 | 0.2563          | 0.2708 |
| 0.6896        | 23.0216 | 12800 | 0.2520          | 0.2700 |
| 0.6645        | 23.7410 | 13200 | 0.2487          | 0.2690 |
| 0.672         | 24.4604 | 13600 | 0.2513          | 0.2697 |
| 0.6551        | 25.1799 | 14000 | 0.2485          | 0.2703 |
| 0.6489        | 25.8993 | 14400 | 0.2501          | 0.2700 |
| 0.6329        | 26.6187 | 14800 | 0.2487          | 0.2697 |
| 0.6639        | 27.3381 | 15200 | 0.2479          | 0.2701 |
| 0.6385        | 28.0576 | 15600 | 0.2489          | 0.2705 |
| 0.6411        | 28.7770 | 16000 | 0.2473          | 0.2705 |
| 0.6462        | 29.4964 | 16400 | 0.2470          | 0.2700 |


### Framework versions

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