You can deploy this model and start earning money today!

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f6

Name: wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-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-DisorderedSpeech-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: 7.5299
Per: 0.0512

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
182.0507	0.7194	400	26.6313	0.1813
113.6896	1.4388	800	14.5825	0.1001
90.3801	2.1583	1200	11.7675	0.0795
79.4812	2.8777	1600	10.5331	0.0703
70.3107	3.5971	2000	9.7714	0.0632
64.2532	4.3165	2400	9.6119	0.0598
60.9918	5.0360	2800	9.0564	0.0589
59.1751	5.7554	3200	8.8780	0.0598
56.4964	6.4748	3600	8.8599	0.0587
54.4957	7.1942	4000	8.5625	0.0580
52.7497	7.9137	4400	8.4239	0.0551
51.8999	8.6331	4800	8.3960	0.0563
49.2083	9.3525	5200	8.2772	0.0545
48.9291	10.0719	5600	8.0716	0.0541
48.7377	10.7914	6000	8.1449	0.0553
47.8504	11.5108	6400	8.3932	0.0550
47.7647	12.2302	6800	8.2615	0.0541
45.202	12.9496	7200	8.2308	0.0520
44.646	13.6691	7600	8.0902	0.0547
45.7588	14.3885	8000	8.1638	0.0536
43.5926	15.1079	8400	7.8015	0.0512
43.8409	15.8273	8800	7.8961	0.0508
42.7911	16.5468	9200	7.7841	0.0512
41.3113	17.2662	9600	7.7777	0.0523
42.4641	17.9856	10000	7.8626	0.0516
41.1045	18.7050	10400	7.7596	0.0526
40.4213	19.4245	10800	7.6734	0.0518
41.133	20.1439	11200	7.6627	0.0525
40.2955	20.8633	11600	7.7543	0.0532
39.5507	21.5827	12000	7.5334	0.0516
40.0653	22.3022	12400	7.6282	0.0520
39.6719	23.0216	12800	7.6222	0.0521
39.5753	23.7410	13200	7.6017	0.0511
39.1713	24.4604	13600	7.5018	0.0506
38.0149	25.1799	14000	7.5360	0.0508
38.1129	25.8993	14400	7.6082	0.0510
37.1463	26.6187	14800	7.5352	0.0506
39.1732	27.3381	15200	7.5984	0.0508
37.571	28.0576	15600	7.5121	0.0518
37.282	28.7770	16000	7.5798	0.0518
37.5821	29.4964	16400	7.5299	0.0512

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-f6

wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-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-DisorderedSpeech-f6