You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

dyu-whisper-base

This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 32
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 500
training_steps: 2000

Training Loss	Epoch	Step	Validation Loss	Wer
3.8111	3.9407	500	1.9069	110.2136
3.2095	7.8775	1000	1.6594	109.9132
3.0454	11.8142	1500	1.6365	105.3738
3.1755	15.7510	2000	1.6362	106.5977

Safetensors

Model size

72.6M params

Tensor type

BF16

Base model

Finetuned

(686)

this model