README.md

metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_keras_callback
model-index:
  - name: whisper_charsplit_new_round2__0057
    results: []

whisper_charsplit_new_round2__0057

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

• Train Loss: 0.0006
• Train Accuracy: 0.0795
• Train Wermet: 7.8589
• Validation Loss: 0.5667
• Validation Accuracy: 0.0769
• Validation Wermet: 7.3058
• Epoch: 56

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
0.0010	0.0795	8.7507	0.5575	0.0767	7.6778	0
0.0013	0.0795	8.9468	0.5652	0.0766	8.3360	1
0.0025	0.0795	8.7338	0.5673	0.0765	8.3770	2
0.0019	0.0795	8.9450	0.5623	0.0766	7.7117	3
0.0011	0.0795	8.9053	0.5609	0.0767	7.5155	4
0.0012	0.0795	8.8862	0.5667	0.0767	8.2913	5
0.0009	0.0795	8.7510	0.5642	0.0766	7.9083	6
0.0037	0.0795	9.3428	0.5717	0.0764	8.2631	7
0.0031	0.0795	9.2135	0.5636	0.0766	8.2384	8
0.0011	0.0795	8.9730	0.5605	0.0767	8.3958	9
0.0005	0.0795	9.3749	0.5552	0.0768	8.0800	10
0.0003	0.0795	9.3340	0.5584	0.0768	8.1322	11
0.0005	0.0795	9.2292	0.5687	0.0767	8.5576	12
0.0037	0.0795	9.2838	0.5751	0.0765	7.4189	13
0.0038	0.0795	8.7270	0.5605	0.0767	7.7098	14
0.0012	0.0795	8.8259	0.5563	0.0768	8.2647	15
0.0005	0.0795	9.0553	0.5620	0.0768	8.5020	16
0.0004	0.0795	9.1734	0.5607	0.0768	8.0252	17
0.0003	0.0795	9.0084	0.5571	0.0769	8.1563	18
0.0014	0.0795	8.7153	0.5804	0.0765	7.8654	19
0.0058	0.0794	8.8460	0.5706	0.0766	7.4342	20
0.0020	0.0795	8.6599	0.5612	0.0767	7.7369	21
0.0007	0.0795	8.6456	0.5543	0.0768	7.4625	22
0.0008	0.0795	8.3246	0.5620	0.0768	7.4475	23
0.0012	0.0795	7.9451	0.5615	0.0768	7.0907	24
0.0025	0.0795	8.1065	0.5619	0.0768	7.7020	25
0.0011	0.0795	8.4237	0.5710	0.0768	7.4035	26
0.0009	0.0795	8.3074	0.5641	0.0768	7.1747	27
0.0007	0.0795	8.5183	0.5688	0.0768	7.4310	28
0.0014	0.0795	8.6604	0.5750	0.0767	8.0751	29
0.0022	0.0795	8.2353	0.5789	0.0767	7.4442	30
0.0019	0.0795	8.6037	0.5715	0.0767	7.6157	31
0.0009	0.0795	8.4768	0.5611	0.0769	7.6392	32
0.0005	0.0795	8.2728	0.5669	0.0768	7.1451	33
0.0010	0.0795	8.1006	0.5918	0.0766	7.4447	34
0.0036	0.0795	8.9171	0.5687	0.0767	7.6962	35
0.0018	0.0795	8.4062	0.5713	0.0768	7.2127	36
0.0012	0.0795	8.3370	0.5683	0.0768	7.1040	37
0.0005	0.0795	7.9931	0.5658	0.0769	6.8043	38
0.0002	0.0795	7.9500	0.5660	0.0769	7.0891	39
0.0001	0.0795	8.1912	0.5632	0.0770	7.1929	40
0.0001	0.0795	8.2484	0.5678	0.0769	7.6993	41
0.0001	0.0795	8.2925	0.5648	0.0770	7.1917	42
0.0001	0.0795	7.9155	0.5752	0.0769	6.4900	43
0.0095	0.0793	8.3244	0.5662	0.0767	6.9524	44
0.0019	0.0795	7.8491	0.5533	0.0769	6.9541	45
0.0006	0.0795	8.0596	0.5573	0.0768	6.9489	46
0.0008	0.0795	8.0277	0.5581	0.0769	6.9081	47
0.0005	0.0795	7.6084	0.5604	0.0769	6.7158	48
0.0006	0.0795	8.0561	0.5729	0.0767	7.4189	49
0.0014	0.0795	8.2875	0.5658	0.0768	7.5768	50
0.0011	0.0795	8.4376	0.5665	0.0768	7.2469	51
0.0018	0.0795	8.3093	0.5771	0.0768	7.2637	52
0.0021	0.0795	7.8370	0.5680	0.0768	7.0030	53
0.0014	0.0795	7.7408	0.5661	0.0769	7.1664	54
0.0009	0.0795	7.7601	0.5639	0.0769	6.9567	55
0.0006	0.0795	7.8589	0.5667	0.0769	7.3058	56

Framework versions

• Transformers 4.32.0.dev0
• TensorFlow 2.12.0
• Tokenizers 0.13.3