metadata
license: mit
base_model: Harveenchadha/vakyansh-wav2vec2-hindi-him-4200
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: hindi_wav2vec2_final_2
results: []
hindi_wav2vec2_final_2
This model is a fine-tuned version of Harveenchadha/vakyansh-wav2vec2-hindi-him-4200 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1054
- Wer: 0.1211
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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.7351 | 10.0 | 25 | 0.9007 | 0.4271 |
| 0.5176 | 20.0 | 50 | 0.3738 | 0.1632 |
| 0.3401 | 30.0 | 75 | 0.1954 | 0.1368 |
| 0.1614 | 40.0 | 100 | 0.1054 | 0.1211 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.14.1