whisper-tiny-sinhala-20k-8k-steps-v2

Ransaka/whisper-tiny-sinhala-20k-8k-steps-v2

whisper-tiny-sinhala-20k-8k-steps-v2 is a automatic speech recognition model from Ransaka. Use it when you need speech turned into text. It is set up for transformers.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

559

Public

Parameters

37.8M

907 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors151 MB · 99%

At a glance

Task: Automatic Speech Recognition
Library: transformers
Model type: whisper
Access: Public
Created: Nov 30, 2023
Updated: Dec 1, 2023
SHA: ef320a3b

Base models

Ransaka/whisper-tiny-sinhala-20k-8k-steps

Datasets

sinhala_asr

Model card

From the Hugging Face model README

whisper-tiny-sinhala-20k-8k-steps-v2

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

Loss: 0.1889
Wer: 51.6357

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: 16
seed: 42
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
0.213	0.53	1000	0.2200	57.9731
0.1611	1.07	2000	0.2017	54.4777
0.1601	1.6	3000	0.1942	53.3355
0.1384	2.13	4000	0.1913	52.2206
0.1101	2.67	5000	0.1889	51.6357

Framework versions

Transformers 4.36.0.dev0
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.15.0

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
Created: Nov 30, 2023
Updated: Dec 1, 2023