MAScIR_elderly_whisper-medium-LoRA

aviroes/MAScIR_elderly_whisper-medium-LoRA

MAScIR_elderly_whisper-medium-LoRA is a machine learning model from aviroes. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

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

Downloads · 30 days

Access

Public

Updated Aug 31, 2023

Repo size

37.9 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin37.9 MB · 96%

At a glance

License: apache-2.0
Access: Public
Created: Aug 31, 2023
Updated: Aug 31, 2023
SHA: 17557a55

Base models

openai/whisper-medium

Model card

From the Hugging Face model README

MAScIR_elderly_whisper-medium-LoRA

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

Loss: 0.0224

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: 0.001
train_batch_size: 8
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: 200
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.3209	0.19	100	0.3262
0.2482	0.37	200	0.3101
0.2726	0.56	300	0.3030
0.2288	0.74	400	0.2848
0.2014	0.93	500	0.2586
0.1277	1.11	600	0.2098
0.1054	1.3	700	0.1857
0.1056	1.48	800	0.1449
0.0842	1.67	900	0.1069
0.0692	1.85	1000	0.0874
0.0314	2.04	1100	0.0628
0.0265	2.22	1200	0.0515
0.0154	2.41	1300	0.0443
0.0127	2.59	1400	0.0382
0.0237	2.78	1500	0.0290
0.0119	2.96	1600	0.0224

Framework versions

Transformers 4.33.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3

License: apache-2.0
Created: Aug 31, 2023
Updated: Aug 31, 2023