whisper-muong-clean-v2

longgb/whisper-muong-clean-v2

whisper-muong-clean-v2 is a machine learning model from longgb. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. 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

Public

Repo size

588 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors126 MB · 60%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Dec 13, 2025
Updated: Dec 13, 2025
SHA: 1b486248

Base models

openai/whisper-large-v3

Model card

From the Hugging Face model README

whisper-muong-clean-v2

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.8842
Wer: 69.7173

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: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
training_steps: 800
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.7886	1.6393	200	0.8212	71.0578
0.3878	3.2787	400	0.7774	66.3295
0.2446	4.9180	600	0.8035	69.9244
0.0913	6.5574	800	0.8842	69.7173

Framework versions

PEFT 0.18.0
Transformers 4.57.3
Pytorch 2.6.0+cu124
Datasets 4.4.1
Tokenizers 0.22.1

Library: peft
License: apache-2.0
Created: Dec 13, 2025
Updated: Dec 13, 2025