metadata

license: apache-2.0
base_model: openai/whisper-tiny.en
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-tiny-en2
    results: []

whisper-tiny-en2

This model is a fine-tuned version of openai/whisper-tiny.en on hf-internal-testing/librispeech_asr_dummy. It achieves the following results on the evaluation set:

Loss: 0.9164
Wer Ortho: 33.1839
Wer: 33.7778

Model description

It is fine-tuned version of whisper-tiny model for the audio/video transcription feature in PersonAI

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: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 600
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.0008	125.0	500	0.9164	33.1839	33.7778

Framework versions

Transformers 4.41.1
Pytorch 2.2.2+cu121
Datasets 2.19.1
Tokenizers 0.19.1