ft-whisper-ja-s

HuyHoang1977/ft-whisper-ja-s

ft-whisper-ja-s is a automatic speech recognition model from HuyHoang1977. 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

1% of all-time downloads

All-time downloads

111

Public

Parameters

72.6M

1.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors290 MB · 99%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: whisper
Access: Public
Created: Sep 25, 2025
Updated: Sep 25, 2025
SHA: 88afcd61

Base models

openai/whisper-base

Model card

From the Hugging Face model README

ft-whisper-ja-s

This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6423
Wer: 88.0131

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: 2e-05
train_batch_size: 32
eval_batch_size: 2
seed: 42
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: cosine
lr_scheduler_warmup_steps: 200
training_steps: 2500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.559	0.9804	500	0.6579	89.3268
0.3999	1.9608	1000	0.6250	89.1626
0.2522	2.9412	1500	0.6278	88.6700
0.1657	3.9216	2000	0.6352	87.8489
0.1294	4.9020	2500	0.6423	88.0131

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
License: apache-2.0
Created: Sep 25, 2025
Updated: Sep 25, 2025