Hugging Face's logo

simran14
/
mr-model-a

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Marathi
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
mr-model-a / README.md
simran14's picture
simran14
End of training
6938662 verified
preview code
|
raw
history blame contribute delete
1.93 kB
metadata
library_name: transformers
language:
  - mr
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: simrank14 Whisper small valA
    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: 7.6095330400854895

simrank14 Whisper small valA

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1047
  • Wer: 7.6095

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: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2254 0.7337 1000 0.1721 12.4531
0.1313 1.4674 2000 0.1047 7.6095

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.1.dev0
  • Tokenizers 0.19.1