You can deploy this model and start earning money today!

alinerodrigues/
wav2vec2-large-xlsr-grosman-1b-words-phoneme-exp-1-v17

Name: wav2vec2-large-xlsr-grosman-1b-words-phoneme-exp-1-v17
Availability: InStock

Views

No views yet

wav2vec2-large-xlsr-grosman-1b-words-phoneme-exp-1-v17

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

More information needed

More information needed

More information needed

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
num_epochs: 200
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Per Hf Metric	Per Avg
2.8576	1.0	102	0.5226	0.1126	0.1409
0.6742	2.0	204	0.3594	0.0759	0.1028
0.5331	3.0	306	0.3266	0.0623	0.0851
0.4415	4.0	408	0.3299	0.0625	0.0884
0.4404	5.0	510	0.3050	0.0598	0.0849
0.4604	6.0	612	0.3934	0.0644	0.0947
0.3908	7.0	714	0.3220	0.0647	0.0904
0.4072	8.0	816	0.4246	0.0641	0.0972
0.363	9.0	918	0.3328	0.0577	0.0821
0.3341	10.0	1020	0.3007	0.0567	0.0782
0.3474	11.0	1122	0.2761	0.0558	0.0758
0.2987	12.0	1224	0.3080	0.0566	0.0799
0.2998	13.0	1326	0.3250	0.0582	0.0811
0.2757	14.0	1428	0.2816	0.0559	0.0804
0.2595	15.0	1530	0.2888	0.0543	0.0766
0.2701	16.0	1632	0.2970	0.0548	0.0753
0.2501	17.0	1734	0.3051	0.0540	0.0758
0.2875	18.0	1836	0.3206	0.0535	0.0764
0.242	19.0	1938	0.2709	0.0527	0.0723
0.263	20.0	2040	0.3993	0.0548	0.0762
0.2424	21.0	2142	0.3492	0.0561	0.0775
0.2283	22.0	2244	0.3061	0.0518	0.0726
0.2306	23.0	2346	0.3173	0.0519	0.0753
0.2349	24.0	2448	0.3656	0.0540	0.0799
0.1944	25.0	2550	0.2957	0.0540	0.0749
0.2157	26.0	2652	0.3922	0.0535	0.0813
0.2233	27.0	2754	0.2984	0.0505	0.0713
0.1991	28.0	2856	0.3150	0.0582	0.0795
0.2121	29.0	2958	0.3140	0.0537	0.0767