metadata
language:
- hi
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Tiny hi - Amit Kayal
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: hi
split: test
args: hi
metrics:
- name: Wer
type: wer
value: 43.87825289464634
Whisper Tiny hi - Amit Kayal
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8996
- Wer: 43.8783
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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2401 | 3.04 | 1000 | 0.5760 | 43.9012 |
| 0.1308 | 7.02 | 2000 | 0.6318 | 42.4768 |
| 0.0399 | 10.05 | 3000 | 0.7560 | 44.2451 |
| 0.0098 | 14.04 | 4000 | 0.8422 | 43.4885 |
| 0.0153 | 18.02 | 5000 | 0.8996 | 43.8783 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.10.0
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2