wav2vec2-base-medical-demo2

srujan00123/wav2vec2-base-medical-demo2

wav2vec2-base-medical-demo2 is a automatic speech recognition model from srujan00123. 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

8% of all-time downloads

All-time downloads

Public

Parameters

315M

2.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.3 GB · 50%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: wav2vec2
Access: Public
Created: Oct 27, 2023
Updated: Nov 25, 2023
SHA: 020c862b

Base models

facebook/wav2vec2-large

Model card

From the Hugging Face model README

wav2vec2-base-medical-demo2

This model is a fine-tuned version of facebook/wav2vec2-large on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4790
Wer: 0.1988

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: 0.0001
train_batch_size: 32
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: 1000
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.8755	3.97	500	1.4725	0.9722
0.8476	7.94	1000	0.5328	0.3881
0.4148	11.9	1500	0.5005	0.2710
0.259	15.87	2000	0.5133	0.2376
0.1795	19.84	2500	0.4084	0.2239
0.1323	23.81	3000	0.4588	0.2067
0.1015	27.78	3500	0.4790	0.1988

Framework versions

Transformers 4.34.1
Pytorch 2.1.0
Datasets 2.14.6
Tokenizers 0.14.1

Task: Automatic Speech Recognition
Library: transformers
Type: wav2vec2
License: apache-2.0
Created: Oct 27, 2023
Updated: Nov 25, 2023