metadata

license: apache-2.0
datasets:
  - thennal/IMaSC
  - vrclc/openslr63
  - vrclc/festvox-iiith-ml
  - smcproject/MSC
language:
  - ml
  - en
base_model: openai/whisper-medium
model-index:
  - name: vrclc/Whisper-med-ml - Bajiyo Baiju
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 13 Malayalam
          type: mozilla-foundation/common_voice_13_0
          config: ml
          split: test
          args: ml
        metrics:
          - type: wer
            value: 63.64
            name: WER
          - type: cer
            value: 13.61
            name: CER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 16 Malayalam
          type: mozilla-foundation/common_voice_16_1
          config: ml
          split: test
          args: ml
        metrics:
          - type: wer
            value: 64.63
            name: WER
          - type: cer
            value: 14.07
            name: CER
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: OpenSLR Malayalam -Test
          type: vrclc/openslr63
          config: ml
          split: test
          args: ml
        metrics:
          - type: wer
            value: 14.65
            name: WER
          - type: cer
            value: 2.59
            name: CER
library_name: transformers

Whisper-med-ml

This model is a fine-tuned version of openai/whisper-medium on the datasets: IMASC, MSC, OpenSLR Malayalam Train split, Festvox Malayalam .

It achieves the following results on the validation set : OpenSLR-Test

Loss: 0.0318
Wer: 14.7300

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: 16
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: 1000
training_steps: 6000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0599	0.4	1000	0.0910	42.4981
0.0341	0.79	2000	0.0584	30.0572
0.0183	1.19	3000	0.0439	23.1650
0.0147	1.58	4000	0.0363	18.7360
0.0107	1.98	5000	0.0322	16.4220
0.0032	2.37	6000	0.0318	14.7300

Framework versions

Transformers 4.37.2
Pytorch 2.1.1+cu121
Datasets 2.16.1
Tokenizers 0.15.1