|
--- |
|
license: apache-2.0 |
|
base_model: DrishtiSharma/wav2vec2-large-xls-r-300m-hi-CV7 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: config-2 |
|
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. --> |
|
|
|
# config-2 |
|
|
|
This model is a fine-tuned version of [DrishtiSharma/wav2vec2-large-xls-r-300m-hi-CV7](https://huggingface.co/DrishtiSharma/wav2vec2-large-xls-r-300m-hi-CV7) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0612 |
|
- Wer: 0.9701 |
|
- Cer: 0.6014 |
|
- Mer: 0.9671 |
|
|
|
## 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: 0.0005 |
|
- 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: 100 |
|
- num_epochs: 40 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Mer | |
|
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:| |
|
| 7.1407 | 1.0050 | 100 | 3.4310 | 0.9999 | 0.9815 | 0.9999 | |
|
| 3.3804 | 2.0101 | 200 | 3.3707 | 1.0 | 0.9582 | 1.0 | |
|
| 3.3051 | 3.0151 | 300 | 3.2022 | 1.0 | 0.9539 | 1.0 | |
|
| 2.6907 | 4.0201 | 400 | 2.0612 | 0.9701 | 0.6014 | 0.9671 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
