README.md

metadata

license: apache-2.0
base_model: bigmorning/whisper_charsplit_new_round2__0061
tags:
  - generated_from_keras_callback
model-index:
  - name: whisper_charsplit_new_round3__0046
    results: []

whisper_charsplit_new_round3__0046

This model is a fine-tuned version of bigmorning/whisper_charsplit_new_round2__0061 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0000
• Train Accuracy: 0.0795
• Train Wermet: 7.7766
• Validation Loss: 0.5639
• Validation Accuracy: 0.0772
• Validation Wermet: 6.8982
• Epoch: 45

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Wermet	Validation Loss	Validation Accuracy	Validation Wermet	Epoch
0.0009	0.0795	7.9492	0.5730	0.0769	7.2856	0
0.0015	0.0795	8.4221	0.5756	0.0769	7.1487	1
0.0012	0.0795	7.8476	0.5699	0.0769	6.5976	2
0.0010	0.0795	7.6843	0.5740	0.0769	6.9513	3
0.0014	0.0795	8.0796	0.5763	0.0768	7.4043	4
0.0019	0.0795	7.7274	0.5724	0.0769	6.4922	5
0.0008	0.0795	7.3468	0.5734	0.0769	6.1909	6
0.0009	0.0795	7.2393	0.5816	0.0769	6.5734	7
0.0010	0.0795	7.5822	0.5755	0.0769	6.6613	8
0.0004	0.0795	7.3807	0.5698	0.0770	7.0671	9
0.0001	0.0795	7.7157	0.5681	0.0771	6.8391	10
0.0001	0.0795	7.7540	0.5725	0.0771	6.9281	11
0.0001	0.0795	7.7721	0.5726	0.0771	6.8911	12
0.0000	0.0795	7.8163	0.5721	0.0771	6.8876	13
0.0000	0.0795	7.7745	0.5741	0.0771	6.8770	14
0.0000	0.0795	7.7277	0.5752	0.0771	6.8671	15
0.0000	0.0795	7.7355	0.5765	0.0771	6.8447	16
0.0000	0.0795	7.7109	0.5784	0.0771	6.8560	17
0.0000	0.0795	7.7427	0.5796	0.0771	6.8406	18
0.0003	0.0795	7.6709	0.6610	0.0762	7.0119	19
0.0115	0.0793	8.3288	0.5580	0.0769	7.1457	20
0.0013	0.0795	8.2537	0.5574	0.0770	6.7708	21
0.0004	0.0795	8.0507	0.5619	0.0770	7.0678	22
0.0003	0.0795	8.0534	0.5593	0.0771	7.0433	23
0.0002	0.0795	8.1738	0.5604	0.0771	7.1617	24
0.0001	0.0795	8.1494	0.5589	0.0771	7.1609	25
0.0000	0.0795	8.2151	0.5614	0.0771	7.1972	26
0.0000	0.0795	8.2332	0.5633	0.0771	7.1736	27
0.0000	0.0795	8.2573	0.5648	0.0771	7.2086	28
0.0000	0.0795	8.2571	0.5667	0.0771	7.1787	29
0.0000	0.0795	8.2607	0.5689	0.0771	7.2107	30
0.0000	0.0795	8.2992	0.5700	0.0772	7.2006	31
0.0000	0.0795	8.3059	0.5721	0.0772	7.2341	32
0.0000	0.0795	8.2872	0.5744	0.0772	7.2069	33
0.0080	0.0794	8.3693	0.5947	0.0762	7.3034	34
0.0063	0.0794	8.2517	0.5491	0.0769	7.1324	35
0.0008	0.0795	7.9115	0.5447	0.0771	6.9422	36
0.0002	0.0795	7.6265	0.5471	0.0771	6.8107	37
0.0001	0.0795	7.6685	0.5493	0.0771	6.6914	38
0.0001	0.0795	7.6100	0.5515	0.0771	6.7738	39
0.0000	0.0795	7.6623	0.5535	0.0771	6.7829	40
0.0000	0.0795	7.6768	0.5556	0.0771	6.8287	41
0.0000	0.0795	7.7199	0.5578	0.0772	6.8398	42
0.0000	0.0795	7.7423	0.5600	0.0772	6.8518	43
0.0000	0.0795	7.7561	0.5617	0.0772	6.8898	44
0.0000	0.0795	7.7766	0.5639	0.0772	6.8982	45

Framework versions

• Transformers 4.32.0.dev0
• TensorFlow 2.12.0
• Tokenizers 0.13.3