metadata

base_model: openai/whisper-small
datasets:
  - mozilla-foundation/common_voice_17_0
language:
  - ps
library_name: transformers.js
license: apache-2.0
tags:
  - generated_from_trainer
  - onnx
model-index:
  - name: Whisper Small PS - Hanif Rahman
    results: []

https://huggingface.co/ihanif/whisper-test with ONNX weights to be compatible with Transformers.js.

Whisper Small PS - Hanif Rahman

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

eval_loss: 0.7573
eval_wer: 46.1819
eval_runtime: 395.7975
eval_samples_per_second: 1.294
eval_steps_per_second: 0.162
epoch: 5.7143
step: 2600

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: 4000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).