You can deploy this model and start earning money today!

zacdan4801/
wav2vec2-lv-60-espeak-cv-ft-WCTC-phocab-ds-f0

Name: wav2vec2-lv-60-espeak-cv-ft-WCTC-phocab-ds-f0
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-f0

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: 60.4523
Per: 0.2231

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
1362.9039	0.7194	400	299.7178	1.0
495.4653	1.4388	800	283.9136	1.0
460.4917	2.1583	1200	236.3290	0.9970
310.7683	2.8777	1600	103.0278	0.4264
173.2595	3.5971	2000	81.5573	0.3225
134.18	4.3165	2400	76.5160	0.2845
114.2295	5.0360	2800	72.5361	0.2633
99.2996	5.7554	3200	72.3879	0.2398
90.7306	6.4748	3600	73.1118	0.2580
87.3973	7.1942	4000	70.3283	0.2458
85.1165	7.9137	4400	69.6865	0.2428
79.1113	8.6331	4800	68.3783	0.2443
75.5191	9.3525	5200	69.2204	0.2420
73.9424	10.0719	5600	69.0756	0.2413
71.5832	10.7914	6000	67.7752	0.2375
68.653	11.5108	6400	67.2984	0.2352
70.9849	12.2302	6800	64.8863	0.2352
67.0436	12.9496	7200	66.1312	0.2436
67.1803	13.6691	7600	65.1860	0.2344
66.1424	14.3885	8000	67.1157	0.2443
62.2517	15.1079	8400	64.2233	0.2291
63.4244	15.8273	8800	65.1356	0.2360
63.3538	16.5468	9200	62.7150	0.2253
62.2757	17.2662	9600	64.0945	0.2344
60.0508	17.9856	10000	62.6389	0.2269
59.6959	18.7050	10400	62.2041	0.2215
60.7711	19.4245	10800	61.9931	0.2261
57.7968	20.1439	11200	62.8550	0.2322
58.7692	20.8633	11600	62.1580	0.2253
55.3977	21.5827	12000	61.0798	0.2246
56.4922	22.3022	12400	62.0927	0.2193
55.8369	23.0216	12800	61.9864	0.2223
55.1164	23.7410	13200	62.4797	0.2238
56.2226	24.4604	13600	61.3560	0.2223
54.7697	25.1799	14000	61.2291	0.2215
54.7076	25.8993	14400	61.3519	0.2261
54.2	26.6187	14800	60.7723	0.2200
54.0033	27.3381	15200	61.0005	0.2215
54.236	28.0576	15600	61.1338	0.2215
53.0723	28.7770	16000	60.8521	0.2238
53.6567	29.4964	16400	60.4523	0.2231

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-f0

wav2vec2-lv-60-espeak-cv-ft-WCTC-phocab-ds-f0

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-f0