whisper-small-ja

lorenzoncina/whisper-small-ja

whisper-small-ja is a automatic speech recognition model from lorenzoncina. 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

18% of all-time downloads

All-time downloads

Public

Repo size

5.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin967 MB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
Model type: whisper
Access: Public
Created: Jan 6, 2023
Updated: Jan 9, 2023
SHA: ce27e8f9

Datasets

mozilla-foundation/common_voice_11_0

Model card

From the Hugging Face model README

Whisper Small JA - Lorenzo Concina

This model is a fine-tuned version of [SVJ Japanese dataset](https://huggingface.co/SVJ Japanese dataset) on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.5596
Cer: 17.7261

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: 4
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: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0682	0.33	1000	0.6098	19.9133
0.0229	0.67	2000	0.5501	18.1911
0.0457	1.0	3000	0.5745	19.3174
0.0123	1.34	4000	0.5315	18.2546
0.0238	1.67	5000	0.5596	17.7261

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0
Datasets 2.7.1
Tokenizers 0.11.0

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
Languages: ja
Created: Jan 6, 2023
Updated: Jan 9, 2023