You can deploy this model and start earning money today!

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f7

Name: wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f7
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-f7

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: 6.6350
Per: 0.0489

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
181.1585	0.7194	400	25.5744	0.1687
112.4511	1.4388	800	13.7963	0.0992
88.6472	2.1583	1200	11.0704	0.0749
77.4292	2.8777	1600	9.6385	0.0681
69.7814	3.5971	2000	9.0049	0.0627
64.6635	4.3165	2400	8.7086	0.0620
60.9746	5.0360	2800	8.5119	0.0601
59.283	5.7554	3200	8.2180	0.0576
55.8485	6.4748	3600	8.1778	0.0563
54.3077	7.1942	4000	8.0386	0.0578
52.5246	7.9137	4400	7.7017	0.0563
50.4818	8.6331	4800	7.6539	0.0548
48.774	9.3525	5200	7.4242	0.0531
48.6169	10.0719	5600	7.4667	0.0554
48.0331	10.7914	6000	7.5428	0.0530
48.3047	11.5108	6400	7.4038	0.0521
47.9103	12.2302	6800	7.2293	0.0511
44.9778	12.9496	7200	7.2455	0.0524
44.6594	13.6691	7600	7.3215	0.0516
44.3842	14.3885	8000	7.2520	0.0497
43.3003	15.1079	8400	7.1036	0.0508
42.8453	15.8273	8800	7.0390	0.0509
43.6585	16.5468	9200	6.9904	0.0501
42.6287	17.2662	9600	7.1549	0.0498
41.5351	17.9856	10000	6.9410	0.0509
40.7262	18.7050	10400	6.9764	0.0497
39.6673	19.4245	10800	6.9377	0.0504
41.151	20.1439	11200	6.8689	0.0482
39.8057	20.8633	11600	6.8659	0.0497
39.6479	21.5827	12000	6.8969	0.0492
40.1821	22.3022	12400	6.8231	0.0497
39.589	23.0216	12800	6.6746	0.0485
39.1111	23.7410	13200	6.6574	0.0492
39.4189	24.4604	13600	6.6123	0.0494
38.4044	25.1799	14000	6.5883	0.0478
38.5939	25.8993	14400	6.6175	0.0478
37.3639	26.6187	14800	6.7044	0.0487
39.1355	27.3381	15200	6.6193	0.0488
36.681	28.0576	15600	6.7399	0.0488
37.702	28.7770	16000	6.6414	0.0490
37.5121	29.4964	16400	6.6350	0.0489

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-f7

wav2vec2-lv-60-espeak-cv-ft-DisorderedSpeech-f7

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-f7