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

nikhilbh/whisper-large-v2-custom-hi

Whisper Large v2 Custom Hi - Nikhil Bhargava

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

nikhilbh/
whisper-large-v2-custom-hi