whisper-small-chinesemed-free_E0-8D0-8 – AI Model by Hanhpt23 | AlphaNeural AI

You can deploy this model and start earning money today!

Hanhpt23/
whisper-small-chinesemed-free_E0-8D0-8

like

0

automatic-speech-recognition

generated_from_trainer

openai/whisper-small

endpoints_compatible

Views

No views yet

openai/whisper-small

This model is a fine-tuned version of openai/whisper-small on the pphuc25/ChiMed dataset. It achieves the following results on the evaluation set:

Loss: 1.0418
Wer: 91.9450
Cer: 39.0820

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: 0.0001
train_batch_size: 8
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: 100
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.5851	1.0	161	0.7381	99.2141	32.0633
0.2895	2.0	322	0.7396	95.4813	32.8654
0.1466	3.0	483	0.8196	97.4460	29.1667
0.0724	4.0	644	0.8459	85.4617	24.9332
0.0519	5.0	805	0.9175	86.2475	31.5954
0.0452	6.0	966	0.9548	82.1218	24.9109
0.0337	7.0	1127	0.9272	82.3183	24.5321
0.0259	8.0	1288	1.0123	91.9450	32.9323
0.0122	9.0	1449	1.0323	80.7466	28.3200
0.0101	10.0	1610	1.0035	82.5147	27.5401
0.0066	11.0	1771	1.0422	81.3360	26.7157
0.0033	12.0	1932	1.0309	81.9253	25.2005
0.0022	13.0	2093	1.0365	82.9077	27.0053
0.0007	14.0	2254	1.0454	83.3006	27.5624
0.0041	15.0	2415	1.0318	89.3910	38.1239
0.0004	16.0	2576	1.0371	89.9804	37.2995
0.0006	17.0	2737	1.0377	90.9627	37.1881
0.0002	18.0	2898	1.0402	91.3556	38.0348
0.0002	19.0	3059	1.0413	91.7485	38.0793
0.0002	20.0	3220	1.0418	91.9450	39.0820

Framework versions

Transformers 4.41.1
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1