wav2vec2-1b-E30_freq_speed – AI Model by Gummybear05 | AlphaNeural AI

You can deploy this model and start earning money today!

Gummybear05/
wav2vec2-1b-E30_freq_speed

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-xls-r-1b

endpoints_compatible

Views

No views yet

wav2vec2-1b-E30_freq_speed

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6382
Cer: 17.3637

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: 0.0001
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
29.1406	0.2580	200	16.8395	83.7289
10.9521	0.5160	400	4.7348	94.3550
9.351	0.7741	600	4.2935	92.1346
7.4517	1.0321	800	4.0701	79.2704
5.4533	1.2901	1000	3.5394	66.4767
3.4356	1.5481	1200	1.6827	37.0301
1.4001	1.8062	1400	1.3482	32.4953
1.063	2.0642	1600	1.1849	32.9359
0.8329	2.3222	1800	1.3395	32.4307
0.7532	2.5802	2000	1.1368	29.5700
0.6628	2.8383	2200	1.0047	28.0545
0.564	3.0963	2400	0.8462	24.4831
0.4531	3.3543	2600	0.7833	19.9366
0.3946	3.6123	2800	0.7219	18.7383
0.3829	3.8703	3000	0.7232	19.0848
0.3109	4.1284	3200	0.7258	19.6370
0.2561	4.3864	3400	0.6731	18.6736
0.2392	4.6444	3600	0.6570	17.9629
0.228	4.9024	3800	0.6382	17.3637

Framework versions

Transformers 4.45.2
Pytorch 2.3.1.post100
Datasets 2.19.1
Tokenizers 0.20.1