whisper-small-ar

AalLaa/whisper-small-ar

whisper-small-ar is a automatic speech recognition model from AalLaa. 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

14% of all-time downloads

All-time downloads

Public

Repo size

4.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin967 MB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: whisper
Access: Public
Created: Dec 28, 2022
Updated: Dec 29, 2022
SHA: d25f040a

Model card

From the Hugging Face model README

whisper-small-ar

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.8342
Wer: 82.3706

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: 2
total_train_batch_size: 16
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

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6454	5.0	1000	1.8790	86.8695
0.0408	10.0	2000	2.4389	80.5579
0.0043	15.0	3000	2.7456	82.2767
0.002	20.0	4000	2.8342	82.3706

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.11.0
Datasets 2.1.0
Tokenizers 0.12.1

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
License: apache-2.0
Created: Dec 28, 2022
Updated: Dec 29, 2022