metadata
library_name: transformers
language:
- mr
base_model: simran14/mr-val-i
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: simrank14 Whisper small val j
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17.0
type: mozilla-foundation/common_voice_17_0
config: mr
split: test
args: mr
metrics:
- name: Wer
type: wer
value: 0.9319317080444345
simrank14 Whisper small val j
This model is a fine-tuned version of simran14/mr-val-i on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2062
- Wer: 0.9319
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: 5e-07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1987 | 1.0152 | 200 | 0.1995 | 1.0835 |
| 0.1482 | 2.0305 | 400 | 0.2078 | 1.0115 |
| 0.0869 | 3.0457 | 600 | 0.2062 | 0.9319 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1