|
--- |
|
library_name: transformers |
|
base_model: Harveenchadha/vakyansh-wav2vec2-nepali-nem-130 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: indic-nepali-finetune-colab-test |
|
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. --> |
|
|
|
# indic-nepali-finetune-colab-test |
|
|
|
This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-nepali-nem-130](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-nepali-nem-130) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 414.3360 |
|
- Wer: 1.0 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- 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 | Wer | |
|
|:-------------:|:-------:|:----:|:---------------:|:---:| |
|
| 5480.8856 | 14.0351 | 400 | 417.9039 | 1.0 | |
|
| 944.0373 | 28.0702 | 800 | 414.3360 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|
