metadata
language:
- hi
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Large v2 Custom Hi - Nikhil Bhargava
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: mozilla-foundation/common_voice_11_0 hi
type: mozilla-foundation/common_voice_11_0
config: hi
split: test
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 0.21857275882502328
Whisper Large v2 Custom Hi - Nikhil Bhargava
This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 hi dataset. It achieves the following results on the evaluation set:
- Loss: 0.3389
- Wer: 0.2186
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0523 | 2.44 | 500 | 0.2123 | 0.2664 |
| 0.0187 | 4.89 | 1000 | 0.2237 | 0.2370 |
| 0.0041 | 7.33 | 1500 | 0.2647 | 0.2310 |
| 0.0028 | 9.78 | 2000 | 0.2904 | 0.2344 |
| 0.0015 | 12.22 | 2500 | 0.2908 | 0.2268 |
| 0.0003 | 14.67 | 3000 | 0.3022 | 0.2197 |
| 0.0003 | 17.11 | 3500 | 0.3249 | 0.2195 |
| 0.0003 | 19.56 | 4000 | 0.3217 | 0.2161 |
| 0.0 | 22.0 | 4500 | 0.3335 | 0.2181 |
| 0.0 | 24.45 | 5000 | 0.3389 | 0.2186 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3