whisper-enhanced-ml

nurzhanit/whisper-enhanced-ml

whisper-enhanced-ml is a automatic speech recognition model from nurzhanit. 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

269

0% of all-time downloads

All-time downloads

186K

Public

Parameters

242M

566 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors967 MB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
Model type: whisper
Access: Public
Created: Dec 23, 2023
Updated: Mar 10, 2025
SHA: e4d2eb8f

Datasets

mozilla-foundation/common_voice_11_0

Model card

From the Hugging Face model README

Whisper Small Hi - Sanchit Gandhi

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

Loss: 0.0002
Wer: 0.0

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: 16
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: 25
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
0.0018	25.0	50	0.0005
0.0002	50.0	100	0.0002
0.0002	75.0	150	0.0002
0.0002	100.0	200	0.0002

Framework versions

Transformers 4.40.0
Pytorch 2.5.0+cu124
Datasets 3.0.2
Tokenizers 0.19.1

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
Languages: hi
Created: Dec 23, 2023
Updated: Mar 10, 2025