You can deploy this model and start earning money today!

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-WCTC-phocab-ds-f6

Name: wav2vec2-lv-60-espeak-cv-ft-WCTC-phocab-ds-f6
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-WCTC-phocab-ds-f6

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: 9.1806
Per: 0.0423

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
1398.6644	0.7194	400	258.6546	1.0
500.7475	1.4388	800	241.2736	1.0
472.2004	2.1583	1200	226.3244	1.0
364.189	2.8777	1600	75.1625	0.3051
181.515	3.5971	2000	36.6363	0.1367
138.4867	4.3165	2400	26.2827	0.0991
117.238	5.0360	2800	21.1678	0.0751
105.612	5.7554	3200	18.0025	0.0635
95.8394	6.4748	3600	15.6192	0.0587
92.017	7.1942	4000	15.2617	0.0587
88.0588	7.9137	4400	14.3011	0.0558
83.2762	8.6331	4800	13.6174	0.0539
81.5538	9.3525	5200	12.1535	0.0520
76.4067	10.0719	5600	12.1355	0.0520
74.3079	10.7914	6000	11.7586	0.0520
71.4132	11.5108	6400	12.2233	0.0529
73.0473	12.2302	6800	11.9576	0.0491
70.7629	12.9496	7200	11.3898	0.0510
68.0968	13.6691	7600	10.6965	0.0491
68.3025	14.3885	8000	11.0596	0.0472
67.8534	15.1079	8400	10.5278	0.0481
65.2577	15.8273	8800	10.5851	0.0443
64.375	16.5468	9200	10.4450	0.0472
64.1679	17.2662	9600	10.2784	0.0452
63.2029	17.9856	10000	10.5400	0.0433
60.9002	18.7050	10400	10.2458	0.0462
60.5609	19.4245	10800	10.0101	0.0462
60.8869	20.1439	11200	9.3618	0.0423
61.6565	20.8633	11600	9.7404	0.0414
59.7346	21.5827	12000	9.8204	0.0472
58.3162	22.3022	12400	10.0092	0.0423
59.1597	23.0216	12800	9.9954	0.0462
58.2877	23.7410	13200	10.0579	0.0443
59.1137	24.4604	13600	9.5583	0.0443
57.1305	25.1799	14000	9.4902	0.0433
57.6542	25.8993	14400	9.7731	0.0433
57.2976	26.6187	14800	9.7321	0.0423
56.3169	27.3381	15200	9.5845	0.0423
57.713	28.0576	15600	9.1392	0.0433
56.2021	28.7770	16000	9.2378	0.0443
55.3441	29.4964	16400	9.1806	0.0423

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-WCTC-phocab-ds-f6

wav2vec2-lv-60-espeak-cv-ft-WCTC-phocab-ds-f6

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-WCTC-phocab-ds-f6