---
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-f0
  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-f0

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: 0.2467
- Per: 0.2758

## 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    |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
| 17.7588       | 0.7194  | 400   | 4.5526          | 0.9854 |
| 4.4442        | 1.4388  | 800   | 4.0728          | 0.9853 |
| 4.0559        | 2.1583  | 1200  | 3.6610          | 0.9853 |
| 3.2947        | 2.8777  | 1600  | 1.7769          | 0.5838 |
| 2.1268        | 3.5971  | 2000  | 0.9135          | 0.3756 |
| 1.6089        | 4.3165  | 2400  | 0.6302          | 0.3189 |
| 1.3977        | 5.0360  | 2800  | 0.4872          | 0.2904 |
| 1.1918        | 5.7554  | 3200  | 0.4154          | 0.2864 |
| 1.1367        | 6.4748  | 3600  | 0.3817          | 0.2827 |
| 1.037         | 7.1942  | 4000  | 0.3461          | 0.2801 |
| 0.9807        | 7.9137  | 4400  | 0.3320          | 0.2802 |
| 0.9281        | 8.6331  | 4800  | 0.3155          | 0.2808 |
| 0.905         | 9.3525  | 5200  | 0.3067          | 0.2780 |
| 0.8613        | 10.0719 | 5600  | 0.3102          | 0.2816 |
| 0.8428        | 10.7914 | 6000  | 0.2961          | 0.2775 |
| 0.8147        | 11.5108 | 6400  | 0.2911          | 0.2773 |
| 0.8135        | 12.2302 | 6800  | 0.2819          | 0.2755 |
| 0.786         | 12.9496 | 7200  | 0.2804          | 0.2753 |
| 0.7666        | 13.6691 | 7600  | 0.2762          | 0.2771 |
| 0.7811        | 14.3885 | 8000  | 0.2806          | 0.2751 |
| 0.7473        | 15.1079 | 8400  | 0.2702          | 0.2758 |
| 0.7336        | 15.8273 | 8800  | 0.2747          | 0.2761 |
| 0.7439        | 16.5468 | 9200  | 0.2702          | 0.2765 |
| 0.6936        | 17.2662 | 9600  | 0.2728          | 0.2755 |
| 0.7077        | 17.9856 | 10000 | 0.2658          | 0.2761 |
| 0.6885        | 18.7050 | 10400 | 0.2613          | 0.2751 |
| 0.6807        | 19.4245 | 10800 | 0.2602          | 0.2775 |
| 0.6994        | 20.1439 | 11200 | 0.2584          | 0.2769 |
| 0.6678        | 20.8633 | 11600 | 0.2589          | 0.2772 |
| 0.6725        | 21.5827 | 12000 | 0.2563          | 0.2761 |
| 0.6641        | 22.3022 | 12400 | 0.2517          | 0.2752 |
| 0.6646        | 23.0216 | 12800 | 0.2515          | 0.2750 |
| 0.6697        | 23.7410 | 13200 | 0.2471          | 0.2755 |
| 0.6632        | 24.4604 | 13600 | 0.2466          | 0.2745 |
| 0.665         | 25.1799 | 14000 | 0.2487          | 0.2757 |
| 0.6375        | 25.8993 | 14400 | 0.2506          | 0.2760 |
| 0.6462        | 26.6187 | 14800 | 0.2502          | 0.2765 |
| 0.6382        | 27.3381 | 15200 | 0.2461          | 0.2767 |
| 0.6546        | 28.0576 | 15600 | 0.2465          | 0.2757 |
| 0.6409        | 28.7770 | 16000 | 0.2454          | 0.2759 |
| 0.6392        | 29.4964 | 16400 | 0.2467          | 0.2758 |


### Framework versions

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