README.md

metadata

language:
  - mr
license: apache-2.0
base_model: simran14/small_8_a
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: simrank14 Whisper small 1B 8e
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: mr
          split: test
          args: mr
        metrics:
          - name: Wer
            type: wer
            value: 18.890597961930396
library_name: transformers
pipeline_tag: automatic-speech-recognition

simrank14 Whisper small 1B 8e

This model is a fine-tuned version of simran14/small_8_a on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5179
• Wer: 18.8906

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: 1e-05
• 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: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.003	3.5587	1000	0.4735	19.5011
0.0002	7.1174	2000	0.5179	18.8906

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 2.20.1.dev0
• Tokenizers 0.19.1