model_broadclass_onSet0.1

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1129
• 0 Precision: 1.0
• 0 Recall: 1.0
• 0 F1-score: 1.0
• 0 Support: 31
• 1 Precision: 0.9259
• 1 Recall: 1.0
• 1 F1-score: 0.9615
• 1 Support: 25
• 2 Precision: 1.0
• 2 Recall: 0.9259
• 2 F1-score: 0.9615
• 2 Support: 27
• 3 Precision: 1.0
• 3 Recall: 1.0
• 3 F1-score: 1.0
• 3 Support: 15
• Accuracy: 0.9796
• Macro avg Precision: 0.9815
• Macro avg Recall: 0.9815
• Macro avg F1-score: 0.9808
• Macro avg Support: 98
• Weighted avg Precision: 0.9811
• Weighted avg Recall: 0.9796
• Weighted avg F1-score: 0.9796
• Weighted avg Support: 98
• Wer: 0.0859
• Mtrix: [[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 2, 25, 0], [3, 0, 0, 0, 15]]

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• 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: 200
• num_epochs: 80
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	0 Precision	0 Recall	0 F1-score	0 Support	1 Precision	1 Recall	1 F1-score	1 Support	2 Precision	2 Recall	2 F1-score	2 Support	3 Precision	3 Recall	3 F1-score	3 Support	Accuracy	Macro avg Precision	Macro avg Recall	Macro avg F1-score	Macro avg Support	Weighted avg Precision	Weighted avg Recall	Weighted avg F1-score	Weighted avg Support	Wer	Mtrix
2.343	4.16	100	2.2083	0.3163	1.0	0.4806	31	0.0	0.0	0.0	25	0.0	0.0	0.0	27	0.0	0.0	0.0	15	0.3163	0.0791	0.25	0.1202	98	0.1001	0.3163	0.1520	98	0.9847	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]]
2.2769	8.33	200	2.1649	0.3163	1.0	0.4806	31	0.0	0.0	0.0	25	0.0	0.0	0.0	27	0.0	0.0	0.0	15	0.3163	0.0791	0.25	0.1202	98	0.1001	0.3163	0.1520	98	0.9847	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]]
1.9687	12.49	300	1.8723	0.3163	1.0	0.4806	31	0.0	0.0	0.0	25	0.0	0.0	0.0	27	0.0	0.0	0.0	15	0.3163	0.0791	0.25	0.1202	98	0.1001	0.3163	0.1520	98	0.9847	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]]
1.8046	16.65	400	1.6982	0.3163	1.0	0.4806	31	0.0	0.0	0.0	25	0.0	0.0	0.0	27	0.0	0.0	0.0	15	0.3163	0.0791	0.25	0.1202	98	0.1001	0.3163	0.1520	98	0.9847	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]]
1.5645	20.82	500	1.5862	0.3163	1.0	0.4806	31	0.0	0.0	0.0	25	0.0	0.0	0.0	27	0.0	0.0	0.0	15	0.3163	0.0791	0.25	0.1202	98	0.1001	0.3163	0.1520	98	0.9847	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]]
1.5322	24.98	600	1.5736	0.3163	1.0	0.4806	31	0.0	0.0	0.0	25	0.0	0.0	0.0	27	0.0	0.0	0.0	15	0.3163	0.0791	0.25	0.1202	98	0.1001	0.3163	0.1520	98	0.9847	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]]
1.5468	29.16	700	1.4736	0.3163	1.0	0.4806	31	0.0	0.0	0.0	25	0.0	0.0	0.0	27	0.0	0.0	0.0	15	0.3163	0.0791	0.25	0.1202	98	0.1001	0.3163	0.1520	98	0.9847	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]]
1.0542	33.33	800	1.0068	0.3163	1.0	0.4806	31	0.0	0.0	0.0	25	0.0	0.0	0.0	27	0.0	0.0	0.0	15	0.3163	0.0791	0.25	0.1202	98	0.1001	0.3163	0.1520	98	0.9847	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 25, 0, 0, 0], [2, 27, 0, 0, 0], [3, 15, 0, 0, 0]]
0.9664	37.49	900	0.9831	0.3483	1.0	0.5167	31	1.0	0.12	0.2143	25	1.0	0.0370	0.0714	27	0.8	0.2667	0.4	15	0.3980	0.7871	0.3559	0.3006	98	0.7632	0.3980	0.2990	98	0.9758	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 21, 3, 0, 1], [2, 26, 0, 1, 0], [3, 11, 0, 0, 4]]
0.9405	41.65	1000	0.9402	0.3827	1.0	0.5536	31	1.0	0.04	0.0769	25	1.0	0.4815	0.65	27	1.0	0.2	0.3333	15	0.4898	0.8457	0.4304	0.4035	98	0.8047	0.4898	0.4248	98	0.9630	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 24, 1, 0, 0], [2, 14, 0, 13, 0], [3, 12, 0, 0, 3]]
0.9341	45.82	1100	0.9330	0.5082	1.0	0.6739	31	0.9231	0.48	0.6316	25	1.0	0.6296	0.7727	27	0.8571	0.4	0.5455	15	0.6735	0.8221	0.6274	0.6559	98	0.8029	0.6735	0.6707	98	0.9497	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 12, 12, 0, 1], [2, 9, 1, 17, 0], [3, 9, 0, 0, 6]]
0.8769	49.98	1200	0.8662	0.6327	1.0	0.775	31	0.9565	0.88	0.9167	25	1.0	0.6296	0.7727	27	0.8889	0.5333	0.6667	15	0.7959	0.8695	0.7607	0.7828	98	0.8557	0.7959	0.7939	98	0.9442	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 2, 22, 0, 1], [2, 9, 1, 17, 0], [3, 7, 0, 0, 8]]
0.8122	54.16	1300	0.7951	0.9062	0.9355	0.9206	31	0.8519	0.92	0.8846	25	1.0	0.8519	0.92	27	0.9375	1.0	0.9677	15	0.9184	0.9239	0.9268	0.9232	98	0.9230	0.9184	0.9185	98	0.9348	[[0, 1, 2, 3], [0, 29, 2, 0, 0], [1, 1, 23, 0, 1], [2, 2, 2, 23, 0], [3, 0, 0, 0, 15]]
0.5747	58.33	1400	0.4843	1.0	1.0	1.0	31	0.96	0.96	0.96	25	1.0	0.9630	0.9811	27	0.9375	1.0	0.9677	15	0.9796	0.9744	0.9807	0.9772	98	0.9802	0.9796	0.9797	98	0.6732	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 24, 0, 1], [2, 0, 1, 26, 0], [3, 0, 0, 0, 15]]
0.2794	62.49	1500	0.2062	1.0	1.0	1.0	31	0.96	0.96	0.96	25	1.0	0.9630	0.9811	27	0.9375	1.0	0.9677	15	0.9796	0.9744	0.9807	0.9772	98	0.9802	0.9796	0.9797	98	0.2236	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 24, 0, 1], [2, 0, 1, 26, 0], [3, 0, 0, 0, 15]]
0.1654	66.65	1600	0.1573	1.0	0.9677	0.9836	31	0.9259	1.0	0.9615	25	1.0	0.9630	0.9811	27	1.0	1.0	1.0	15	0.9796	0.9815	0.9827	0.9816	98	0.9811	0.9796	0.9798	98	0.1303	[[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 25, 0, 0], [2, 0, 1, 26, 0], [3, 0, 0, 0, 15]]
0.1092	70.82	1700	0.1451	1.0	0.9677	0.9836	31	0.8889	0.96	0.9231	25	1.0	0.9259	0.9615	27	0.9375	1.0	0.9677	15	0.9592	0.9566	0.9634	0.9590	98	0.9621	0.9592	0.9597	98	0.1056	[[0, 1, 2, 3], [0, 30, 1, 0, 0], [1, 0, 24, 0, 1], [2, 0, 2, 25, 0], [3, 0, 0, 0, 15]]
0.085	74.98	1800	0.1126	1.0	1.0	1.0	31	0.9259	1.0	0.9615	25	1.0	0.9259	0.9615	27	1.0	1.0	1.0	15	0.9796	0.9815	0.9815	0.9808	98	0.9811	0.9796	0.9796	98	0.0938	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 2, 25, 0], [3, 0, 0, 0, 15]]
0.0824	79.16	1900	0.1118	1.0	1.0	1.0	31	0.9259	1.0	0.9615	25	1.0	0.9259	0.9615	27	1.0	1.0	1.0	15	0.9796	0.9815	0.9815	0.9808	98	0.9811	0.9796	0.9796	98	0.0859	[[0, 1, 2, 3], [0, 31, 0, 0, 0], [1, 0, 25, 0, 0], [2, 0, 2, 25, 0], [3, 0, 0, 0, 15]]

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2