You can deploy this model and start earning money today!

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f3

Name: wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f3
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-f3

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: 8.3741
Per: 0.0587

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
181.7856	0.7194	400	25.7933	0.1749
113.7814	1.4388	800	15.3820	0.1048
88.8629	2.1583	1200	12.7374	0.0870
78.4998	2.8777	1600	11.6487	0.0779
70.4043	3.5971	2000	11.0928	0.0726
64.3341	4.3165	2400	10.8236	0.0732
62.6328	5.0360	2800	10.3035	0.0698
58.3976	5.7554	3200	10.1864	0.0697
57.3604	6.4748	3600	10.0237	0.0658
53.6597	7.1942	4000	9.9813	0.0655
53.0714	7.9137	4400	9.6314	0.0640
51.7553	8.6331	4800	9.3768	0.0642
48.5305	9.3525	5200	9.4268	0.0637
48.7839	10.0719	5600	9.3001	0.0620
47.7837	10.7914	6000	9.0760	0.0610
48.6449	11.5108	6400	9.0312	0.0612
45.4065	12.2302	6800	8.9609	0.0616
45.1974	12.9496	7200	9.1487	0.0629
44.41	13.6691	7600	9.0656	0.0630
43.4332	14.3885	8000	8.9302	0.0620
42.9728	15.1079	8400	8.9771	0.0616
42.8819	15.8273	8800	8.7602	0.0605
42.4677	16.5468	9200	8.8350	0.0631
41.1923	17.2662	9600	8.7029	0.0615
41.4966	17.9856	10000	8.7241	0.0605
40.8476	18.7050	10400	8.5715	0.0608
39.2658	19.4245	10800	8.7673	0.0608
39.6557	20.1439	11200	8.6285	0.0605
39.8852	20.8633	11600	8.5821	0.0593
38.8559	21.5827	12000	8.5691	0.0600
39.7784	22.3022	12400	8.6123	0.0601
39.1787	23.0216	12800	8.4574	0.0594
38.8014	23.7410	13200	8.3464	0.0605
38.4732	24.4604	13600	8.5222	0.0584
38.001	25.1799	14000	8.4287	0.0593
38.0697	25.8993	14400	8.4568	0.0587
36.928	26.6187	14800	8.4201	0.0597
38.6695	27.3381	15200	8.4379	0.0586
36.9873	28.0576	15600	8.3489	0.0586
37.661	28.7770	16000	8.3904	0.0586
37.3612	29.4964	16400	8.3741	0.0587

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-f3

wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f3

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-f3