whisper-large-v2-AiHub

byoussef/whisper-large-v2-AiHub

whisper-large-v2-AiHub is a automatic speech recognition model from byoussef. 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

6% of all-time downloads

All-time downloads

Public

Repo size

43.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin6.2 GB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: whisper
Access: Public
Created: Mar 23, 2023
Updated: Mar 28, 2023
SHA: 1931b521

Model card

From the Hugging Face model README

whisper-large-v2-AiHub

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2622
Wer: 0.2232

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: 32
eval_batch_size: 32
seed: 42
distributed_type: multi-GPU
num_devices: 7
total_train_batch_size: 224
total_eval_batch_size: 224
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3373	0.1	1000	0.3146	0.2507
0.3131	0.2	2000	0.2967	0.2408
0.3053	0.3	3000	0.2815	0.2346
0.2812	0.4	4000	0.2695	0.2267
0.2765	0.5	5000	0.2623	0.2230

Framework versions

Transformers 4.27.0.dev0
Pytorch 1.12.1+cu113
Datasets 2.10.1
Tokenizers 0.13.2

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
License: apache-2.0
Created: Mar 23, 2023
Updated: Mar 28, 2023