You can deploy this model and start earning money today!

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f2

Name: wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f2
Availability: InStock

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-lv-60-espeak-cv-ft

finetune

apache-2.0

endpoints_compatible

Views

No views yet

wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f2

This model is a fine-tuned version of facebook/wav2vec2-lv-60-espeak-cv-ft on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 8.6151
Per: 0.0571

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: 3e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Per
181.9981	0.7194	400	27.8881	0.1846
114.999	1.4388	800	15.9528	0.1038
89.6854	2.1583	1200	12.9923	0.0840
79.6321	2.8777	1600	11.5980	0.0778
70.6254	3.5971	2000	11.3928	0.0742
64.184	4.3165	2400	10.9484	0.0700
60.8741	5.0360	2800	10.4352	0.0691
58.509	5.7554	3200	10.4791	0.0678
56.6584	6.4748	3600	9.9769	0.0684
54.7788	7.1942	4000	9.8292	0.0649
53.7326	7.9137	4400	9.6234	0.0666
51.2859	8.6331	4800	9.3399	0.0644
49.2551	9.3525	5200	9.5392	0.0659
49.2123	10.0719	5600	9.3082	0.0653
48.2361	10.7914	6000	9.5114	0.0640
47.5498	11.5108	6400	9.2966	0.0634
46.5783	12.2302	6800	9.1043	0.0641
44.6874	12.9496	7200	9.1437	0.0619
44.9206	13.6691	7600	9.2164	0.0617
44.6649	14.3885	8000	8.9514	0.0620
42.7664	15.1079	8400	9.0018	0.0603
43.2099	15.8273	8800	9.1339	0.0615
41.7664	16.5468	9200	9.1218	0.0615
41.2509	17.2662	9600	8.7165	0.0628
42.1306	17.9856	10000	8.7418	0.0612
40.6004	18.7050	10400	8.7290	0.0613
40.3318	19.4245	10800	8.8177	0.0610
40.5477	20.1439	11200	8.6978	0.0592
39.5209	20.8633	11600	8.6752	0.0599
39.9304	21.5827	12000	8.5835	0.0589
39.6353	22.3022	12400	8.7486	0.0592
38.7429	23.0216	12800	8.5193	0.0583
39.3688	23.7410	13200	8.5237	0.0605
39.454	24.4604	13600	8.4845	0.0577
37.9337	25.1799	14000	8.5230	0.0576
39.0868	25.8993	14400	8.3876	0.0577
37.7724	26.6187	14800	8.4580	0.0567
38.2316	27.3381	15200	8.5631	0.0583
37.1652	28.0576	15600	8.5211	0.0572
37.7524	28.7770	16000	8.5743	0.0574
37.3678	29.4964	16400	8.6151	0.0571

Framework versions

Transformers 4.57.6
Pytorch 2.9.1+cu128
Datasets 4.5.0
Tokenizers 0.22.2

zacdan4801/wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f2

wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f2