whisper-finetuned-2

SahaRobotik/whisper-finetuned-2

whisper-finetuned-2 is a automatic speech recognition model from SahaRobotik. Use it when you need speech turned into text. The card lists the license as apache-2.0.

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

Downloads · 30 days

7% of all-time downloads

All-time downloads

135

Public

Parameters

764M

15.3 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors3.1 GB · 100%

At a glance

Task: Automatic Speech Recognition
License: apache-2.0
Model type: whisper
Access: Public
Created: Aug 9, 2024
Updated: Oct 8, 2024
SHA: a6d90214

Base models

openai/whisper-medium

Datasets

mozilla-foundation/common_voice_11_0

Model card

From the Hugging Face model README

Whisper Medium Tr

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.1577
Wer: 11.4187

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
training_steps: 200
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0027	4.4444	50	0.1648	10.0923
0.0011	8.8889	100	0.1786	12.0531
0.0001	13.3333	150	0.1590	11.3610
0.0	17.7778	200	0.1577	11.4187

Framework versions

Transformers 4.43.2
Pytorch 2.3.1+cu121
Datasets 2.19.2
Tokenizers 0.19.1

Task: Automatic Speech Recognition
Type: whisper
License: apache-2.0
Languages: tr
Created: Aug 9, 2024
Updated: Oct 8, 2024