You can deploy this model and start earning money today!

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f5

Name: wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f5
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-f5

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: 7.5449
Per: 0.0537

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
181.852	0.7194	400	27.8784	0.1855
114.0923	1.4388	800	15.6536	0.1058
90.1094	2.1583	1200	12.2288	0.0806
79.2337	2.8777	1600	10.9994	0.0760
71.119	3.5971	2000	10.2717	0.0702
64.9755	4.3165	2400	9.7363	0.0659
62.7615	5.0360	2800	9.5184	0.0661
58.6825	5.7554	3200	9.7133	0.0660
57.306	6.4748	3600	9.0388	0.0625
54.9784	7.1942	4000	8.7182	0.0591
53.1441	7.9137	4400	8.8336	0.0591
51.5663	8.6331	4800	8.7232	0.0584
49.008	9.3525	5200	8.6572	0.0598
49.7989	10.0719	5600	8.3993	0.0598
48.5647	10.7914	6000	8.3477	0.0579
48.3604	11.5108	6400	8.0833	0.0562
46.629	12.2302	6800	8.2354	0.0572
45.5776	12.9496	7200	8.0368	0.0550
44.7275	13.6691	7600	7.9766	0.0550
44.8643	14.3885	8000	8.0321	0.0567
43.4087	15.1079	8400	8.0589	0.0568
43.53	15.8273	8800	8.0456	0.0553
43.2206	16.5468	9200	7.9601	0.0549
41.0633	17.2662	9600	7.9241	0.0561
42.0394	17.9856	10000	7.8002	0.0543
40.1351	18.7050	10400	7.8771	0.0547
40.2766	19.4245	10800	7.6888	0.0544
40.3536	20.1439	11200	7.6978	0.0549
40.3643	20.8633	11600	7.6727	0.0533
39.2305	21.5827	12000	7.7237	0.0528
40.1355	22.3022	12400	7.5083	0.0528
38.6954	23.0216	12800	7.6898	0.0530
39.7588	23.7410	13200	7.6747	0.0538
38.5935	24.4604	13600	7.6341	0.0535
39.0636	25.1799	14000	7.5990	0.0549
37.8873	25.8993	14400	7.5050	0.0543
36.2248	26.6187	14800	7.5571	0.0539
38.6287	27.3381	15200	7.5671	0.0534
36.914	28.0576	15600	7.5464	0.0530
37.4371	28.7770	16000	7.5664	0.0535
36.2044	29.4964	16400	7.5449	0.0537

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-f5

wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f5

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-f5