metadata
license: apache-2.0
base_model: Harveenchadha/hindi_base_wav2vec2
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: hindi_beekeeping_wav2vec2-2
results: []
hindi_beekeeping_wav2vec2-2
This model is a fine-tuned version of Harveenchadha/hindi_base_wav2vec2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7999
- Wer: 0.3017
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: 10
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3186 | 5.56 | 25 | 0.5615 | 0.2890 |
| 0.0831 | 11.11 | 50 | 1.0522 | 0.4262 |
| 0.0499 | 16.67 | 75 | 0.7605 | 0.3354 |
| 0.0518 | 22.22 | 100 | 0.6797 | 0.3713 |
| 0.0355 | 27.78 | 125 | 0.8345 | 0.3333 |
| 0.0284 | 33.33 | 150 | 0.8702 | 0.3608 |
| 0.0248 | 38.89 | 175 | 0.7246 | 0.3734 |
| 0.0229 | 44.44 | 200 | 0.7885 | 0.3291 |
| 0.0193 | 50.0 | 225 | 0.8082 | 0.3312 |
| 0.0164 | 55.56 | 250 | 0.7141 | 0.3186 |
| 0.0109 | 61.11 | 275 | 0.9168 | 0.3333 |
| 0.0082 | 66.67 | 300 | 0.9048 | 0.3418 |
| 0.007 | 72.22 | 325 | 0.9089 | 0.3080 |
| 0.0074 | 77.78 | 350 | 0.8113 | 0.2911 |
| 0.0053 | 83.33 | 375 | 0.8197 | 0.3186 |
| 0.0065 | 88.89 | 400 | 0.7999 | 0.3017 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1