Hugging Face's logo

CSY1109
/
drone_test1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Model card Files Metrics Community
CSY1109 commited on
Commit
ef5298b
·
verified ·
1 Parent(s): ac38be2

End of training

Browse files
Files changed (3) hide show
  1. README.md +28 -31
  2. model.safetensors +1 -1
  3. runs/Feb24_17-19-40_ubuntu-Alienware-m15-R7/events.out.tfevents.1740388789.ubuntu-Alienware-m15-R7.19536.1 +2 -2
README.md CHANGED
@@ -6,24 +6,11 @@ license: apache-2.0
6
  base_model: openai/whisper-small
7
  tags:
8
  - generated_from_trainer
9
- datasets:
10
- - mozilla-foundation/common_voice_19_0
11
  metrics:
12
  - wer
13
  model-index:
14
  - name: Drone test En - Siang Yi
15
- results:
16
- - task:
17
- name: Automatic Speech Recognition
18
- type: automatic-speech-recognition
19
- dataset:
20
- name: drone command test1
21
- type: mozilla-foundation/common_voice_19_0
22
- args: 'config: hi, split: test'
23
- metrics:
24
- - name: Wer
25
- type: wer
26
- value: 1.680672268907563
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # Drone test En - Siang Yi
33
 
34
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the drone command test1 dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.0224
37
- - Wer: 1.6807
38
 
39
  ## Model description
40
 
@@ -53,7 +40,7 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 1e-05
57
  - train_batch_size: 4
58
  - eval_batch_size: 4
59
  - seed: 42
@@ -62,23 +49,33 @@ The following hyperparameters were used during training:
62
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
- - training_steps: 100
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
- | Training Loss | Epoch | Step | Validation Loss | Wer |
71
- |:-------------:|:-----:|:----:|:---------------:|:------:|
72
- | 0.6591 | 2.5 | 10 | 0.4098 | 5.0420 |
73
- | 0.1945 | 5.0 | 20 | 0.0645 | 1.6807 |
74
- | 0.029 | 7.5 | 30 | 0.0416 | 1.6807 |
75
- | 0.0077 | 10.0 | 40 | 0.0416 | 1.6807 |
76
- | 0.0013 | 12.5 | 50 | 0.0232 | 1.6807 |
77
- | 0.0006 | 15.0 | 60 | 0.0216 | 1.6807 |
78
- | 0.0004 | 17.5 | 70 | 0.0220 | 1.6807 |
79
- | 0.0004 | 20.0 | 80 | 0.0223 | 1.6807 |
80
- | 0.0004 | 22.5 | 90 | 0.0224 | 1.6807 |
81
- | 0.0004 | 25.0 | 100 | 0.0224 | 1.6807 |
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
 
6
  base_model: openai/whisper-small
7
  tags:
8
  - generated_from_trainer
 
 
9
  metrics:
10
  - wer
11
  model-index:
12
  - name: Drone test En - Siang Yi
13
+ results: []
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
18
 
19
  # Drone test En - Siang Yi
20
 
21
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the drone command test2 dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0264
24
+ - Wer: 15.9664
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 3e-05
44
  - train_batch_size: 4
45
  - eval_batch_size: 4
46
  - seed: 42
 
49
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_ratio: 0.1
52
+ - training_steps: 200
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
58
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
59
+ | 0.0 | 2.5 | 10 | 0.0189 | 15.9664 |
60
+ | 0.0 | 5.0 | 20 | 0.0076 | 15.9664 |
61
+ | 0.0005 | 7.5 | 30 | 0.0067 | 15.9664 |
62
+ | 0.0013 | 10.0 | 40 | 0.0118 | 14.2857 |
63
+ | 0.0008 | 12.5 | 50 | 0.0140 | 15.9664 |
64
+ | 0.0001 | 15.0 | 60 | 0.0204 | 15.9664 |
65
+ | 0.0 | 17.5 | 70 | 0.0215 | 15.9664 |
66
+ | 0.0 | 20.0 | 80 | 0.0228 | 15.9664 |
67
+ | 0.0 | 22.5 | 90 | 0.0237 | 15.9664 |
68
+ | 0.0 | 25.0 | 100 | 0.0245 | 15.9664 |
69
+ | 0.0 | 27.5 | 110 | 0.0251 | 15.9664 |
70
+ | 0.0 | 30.0 | 120 | 0.0255 | 15.9664 |
71
+ | 0.0 | 32.5 | 130 | 0.0257 | 15.9664 |
72
+ | 0.0 | 35.0 | 140 | 0.0259 | 15.9664 |
73
+ | 0.0 | 37.5 | 150 | 0.0260 | 15.9664 |
74
+ | 0.0 | 40.0 | 160 | 0.0262 | 15.9664 |
75
+ | 0.0 | 42.5 | 170 | 0.0262 | 15.9664 |
76
+ | 0.0 | 45.0 | 180 | 0.0263 | 15.9664 |
77
+ | 0.0 | 47.5 | 190 | 0.0263 | 15.9664 |
78
+ | 0.0 | 50.0 | 200 | 0.0264 | 15.9664 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b81de194b2a548f479b8040725ec6ac28ad7e366a5b3372d97a636ce227f794
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7bbe25472e005dc8629d922d7849d5c5fd2267135d76b5ff70b158edbd01f2
3
  size 966995080
runs/Feb24_17-19-40_ubuntu-Alienware-m15-R7/events.out.tfevents.1740388789.ubuntu-Alienware-m15-R7.19536.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b33647c4da97b3204973d98d2119da64f5eaba6ea124cc13cf5eeb137d6f26d
3
- size 17613
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd677b690d328b15b0f6e869c4e6ff18619500d51582362a4c00c4d7f36ce62
3
+ size 20927