whisper-small.en

crossdelenna/whisper-small.en

whisper-small.en is a automatic speech recognition model from crossdelenna. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

124

6% of all-time downloads

All-time downloads

2.2K

Public

Parameters

242M

218 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin967 MB · 50%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: whisper
Access: Public
Created: Apr 3, 2023
Updated: Jul 20, 2024
SHA: 3d1f5c72

Model card

From the Hugging Face model README

whisper-small.en

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

Loss: 0.0004
Wer: 0.7672

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: 10
training_steps: 1401
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0047	1.03	400	0.0037	0.9334
0.0033	2.06	800	0.0012	0.7416
0.0011	3.09	1200	0.0004	0.7672

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
License: apache-2.0
Created: Apr 3, 2023
Updated: Jul 20, 2024