whisper-small-Encode-chinesemed – AI Model by Hanhpt23 | AlphaNeural AI

You can deploy this model and start earning money today!

Hanhpt23/
whisper-small-Encode-chinesemed

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: 1.3249
Cer: 27.8520

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	Cer
0.776	1.0	161	0.9761	346.2567
0.4431	2.0	322	0.9469	55.4813
0.2522	3.0	483	1.1108	47.6381
0.1548	4.0	644	1.1770	33.2219
0.1216	5.0	805	1.2831	34.9822
0.0914	6.0	966	1.2727	31.5285
0.0799	7.0	1127	1.2785	33.9795
0.0503	8.0	1288	1.3214	41.1542
0.0577	9.0	1449	1.3421	31.4394
0.0316	10.0	1610	1.3284	35.1381
0.0249	11.0	1771	1.3602	30.2139
0.0245	12.0	1932	1.3494	32.3752
0.0199	13.0	2093	1.3304	30.7041
0.0126	14.0	2254	1.3625	30.6818
0.0039	15.0	2415	1.3302	29.3895
0.003	16.0	2576	1.3131	29.1444
0.0003	17.0	2737	1.3168	28.3422
0.0003	18.0	2898	1.3202	28.0526
0.0007	19.0	3059	1.3235	27.9857
0.0003	20.0	3220	1.3249	27.8520

Framework versions

Transformers 4.41.1
Pytorch 2.3.0
Datasets 2.19.1
Tokenizers 0.19.1