whisper_input_decoder_equal_labels_no_force__0045

bigmorning/whisper_input_decoder_equal_labels_no_force__0045

whisper_input_decoder_equal_labels_no_force__0045 is a automatic speech recognition model from bigmorning. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.

probably proofread and complete it, then remove this comment. --

Downloads · 30 days

4% of all-time downloads

All-time downloads

Public

Repo size

151 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.h5151 MB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: whisper
Access: Public
Created: Sep 4, 2023
Updated: Sep 4, 2023
SHA: 6cc2e181

Base models

openai/whisper-tiny

Model card

From the Hugging Face model README

whisper_input_decoder_equal_labels_no_force__0045

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: 0.0000
Train Accuracy: 0.0362
Train Wermet: 0.0172
Validation Loss: 0.0002
Validation Accuracy: 0.0266
Validation Wermet: 0.0210
Epoch: 44

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
0.7688	0.0332	32.0424	0.0164	0.0265	57.8712	0
0.0114	0.0362	31.1067	0.0062	0.0266	54.8371	1
0.0048	0.0362	27.0610	0.0030	0.0266	50.1428	2
0.0027	0.0362	24.9672	0.0018	0.0266	48.0741	3
0.0018	0.0362	23.1500	0.0013	0.0266	44.9304	4
0.0013	0.0362	21.5445	0.0010	0.0266	42.3508	5
0.0009	0.0362	20.2775	0.0008	0.0266	40.4061	6
0.0007	0.0362	19.5082	0.0006	0.0266	38.2329	7
0.0005	0.0362	17.9967	0.0005	0.0266	35.9761	8
0.0004	0.0362	16.8461	0.0004	0.0266	34.1220	9
0.0003	0.0362	15.8373	0.0004	0.0266	32.0054	10
0.0003	0.0362	14.7685	0.0004	0.0266	29.6994	11
0.0002	0.0362	13.4142	0.0003	0.0266	27.1796	12
0.0002	0.0362	12.4809	0.0003	0.0266	25.3421	13
0.0002	0.0362	11.2286	0.0003	0.0266	23.1619	14
0.0001	0.0362	10.2408	0.0003	0.0266	21.3348	15
0.0001	0.0362	9.5439	0.0002	0.0266	20.1758	16
0.0001	0.0362	8.7578	0.0002	0.0266	18.3977	17
0.0001	0.0362	7.8698	0.0002	0.0266	16.2156	18
0.0001	0.0362	7.0007	0.0002	0.0266	14.7919	19
0.0001	0.0362	6.2610	0.0002	0.0266	13.0212	20
0.0001	0.0362	5.5103	0.0002	0.0266	11.5619	21
0.0000	0.0362	4.9163	0.0002	0.0266	10.4626	22
0.0000	0.0362	4.3166	0.0002	0.0266	9.2446	23
0.0000	0.0362	3.7524	0.0002	0.0266	7.7431	24
0.0000	0.0362	3.2129	0.0002	0.0266	6.6332	25
0.0000	0.0362	2.7739	0.0002	0.0266	5.7615	26
0.0000	0.0362	2.3764	0.0002	0.0266	4.9058	27
0.0000	0.0362	1.9780	0.0002	0.0266	4.0666	28
0.0000	0.0362	1.6255	0.0002	0.0266	3.3591	29
0.0000	0.0362	1.3291	0.0002	0.0266	2.7223	30
0.0000	0.0362	1.1012	0.0002	0.0266	2.1768	31
0.0000	0.0362	0.9017	0.0002	0.0266	1.7957	32
0.0000	0.0362	0.7347	0.0002	0.0266	1.3240	33
0.0000	0.0362	0.5807	0.0002	0.0266	0.9770	34
0.0000	0.0362	0.4562	0.0002	0.0266	0.7842	35
0.0000	0.0362	0.3738	0.0002	0.0266	0.6098	36
0.0000	0.0362	0.2925	0.0002	0.0266	0.4481	37
0.0000	0.0362	0.2142	0.0002	0.0266	0.3331	38
0.0000	0.0362	0.1491	0.0002	0.0266	0.2229	39
0.0000	0.0362	0.0935	0.0002	0.0266	0.1604	40
0.0000	0.0362	0.0588	0.0002	0.0266	0.1018	41
0.0000	0.0362	0.0421	0.0002	0.0266	0.0653	42
0.0000	0.0362	0.0284	0.0002	0.0266	0.0364	43
0.0000	0.0362	0.0172	0.0002	0.0266	0.0210	44

Framework versions

Transformers 4.33.0.dev0
TensorFlow 2.13.0
Tokenizers 0.13.3

Task: Automatic Speech Recognition
Library: transformers
Type: whisper
License: apache-2.0
Created: Sep 4, 2023
Updated: Sep 4, 2023