Hugging Face's logo

razhan
/
whisper-base-lki

Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
razhan commited on
Commit
6cbaa6f
·
verified ·
1 Parent(s): 101366d

End of training

Browse files
Files changed (5) hide show
  1. README.md +15 -2
  2. all_results.json +16 -0
  3. eval_results.json +10 -0
  4. train_results.json +9 -0
  5. trainer_state.json +99 -0
README.md CHANGED
@@ -4,11 +4,24 @@ license: apache-2.0
4
  base_model: openai/whisper-base
5
  tags:
6
  - generated_from_trainer
 
 
7
  metrics:
8
  - wer
9
  model-index:
10
  - name: whisper-base-lki
11
- results: []
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,7 +29,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # whisper-base-lki
18
 
19
- This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 4.0246
22
  - Wer: 1.1130
 
4
  base_model: openai/whisper-base
5
  tags:
6
  - generated_from_trainer
7
+ datasets:
8
+ - razhan/DOLMA-speech
9
  metrics:
10
  - wer
11
  model-index:
12
  - name: whisper-base-lki
13
+ results:
14
+ - task:
15
+ name: Automatic Speech Recognition
16
+ type: automatic-speech-recognition
17
+ dataset:
18
+ name: razhan/DOLMA-speech laki_kurdish
19
+ type: razhan/DOLMA-speech
20
+ args: laki_kurdish
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 1.113034875092753
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  # whisper-base-lki
31
 
32
+ This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the razhan/DOLMA-speech laki_kurdish dataset.
33
  It achieves the following results on the evaluation set:
34
  - Loss: 4.0246
35
  - Wer: 1.1130
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_cer": 0.5701466189378709,
4
+ "eval_loss": 4.024605751037598,
5
+ "eval_runtime": 36.7376,
6
+ "eval_samples": 313,
7
+ "eval_samples_per_second": 8.52,
8
+ "eval_steps_per_second": 0.054,
9
+ "eval_wer": 1.113034875092753,
10
+ "total_flos": 2.4906238324113408e+17,
11
+ "train_loss": 4.0161895751953125,
12
+ "train_runtime": 411.106,
13
+ "train_samples": 755,
14
+ "train_samples_per_second": 9.183,
15
+ "train_steps_per_second": 0.024
16
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_cer": 0.5701466189378709,
4
+ "eval_loss": 4.024605751037598,
5
+ "eval_runtime": 36.7376,
6
+ "eval_samples": 313,
7
+ "eval_samples_per_second": 8.52,
8
+ "eval_steps_per_second": 0.054,
9
+ "eval_wer": 1.113034875092753
10
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 2.4906238324113408e+17,
4
+ "train_loss": 4.0161895751953125,
5
+ "train_runtime": 411.106,
6
+ "train_samples": 755,
7
+ "train_samples_per_second": 9.183,
8
+ "train_steps_per_second": 0.024
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_cer": 0.5721080763006914,
14
+ "eval_loss": 4.031211853027344,
15
+ "eval_runtime": 36.4445,
16
+ "eval_samples_per_second": 8.588,
17
+ "eval_steps_per_second": 0.055,
18
+ "eval_wer": 1.1142715805095227,
19
+ "step": 2
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_cer": 0.5721080763006914,
24
+ "eval_loss": 4.031211853027344,
25
+ "eval_runtime": 35.8435,
26
+ "eval_samples_per_second": 8.732,
27
+ "eval_steps_per_second": 0.056,
28
+ "eval_wer": 1.1142715805095227,
29
+ "step": 4
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_cer": 0.5721080763006914,
34
+ "eval_loss": 4.031211853027344,
35
+ "eval_runtime": 36.3205,
36
+ "eval_samples_per_second": 8.618,
37
+ "eval_steps_per_second": 0.055,
38
+ "eval_wer": 1.1142715805095227,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 4.0,
43
+ "eval_cer": 0.5720590398666209,
44
+ "eval_loss": 4.030923366546631,
45
+ "eval_runtime": 35.7931,
46
+ "eval_samples_per_second": 8.745,
47
+ "eval_steps_per_second": 0.056,
48
+ "eval_wer": 1.1137768983428147,
49
+ "step": 8
50
+ },
51
+ {
52
+ "epoch": 5.0,
53
+ "grad_norm": 66.4626693725586,
54
+ "learning_rate": 4.0000000000000003e-07,
55
+ "loss": 4.0162,
56
+ "step": 10
57
+ },
58
+ {
59
+ "epoch": 5.0,
60
+ "eval_cer": 0.5701466189378709,
61
+ "eval_loss": 4.024605751037598,
62
+ "eval_runtime": 35.8347,
63
+ "eval_samples_per_second": 8.735,
64
+ "eval_steps_per_second": 0.056,
65
+ "eval_wer": 1.113034875092753,
66
+ "step": 10
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "step": 10,
71
+ "total_flos": 2.4906238324113408e+17,
72
+ "train_loss": 4.0161895751953125,
73
+ "train_runtime": 411.106,
74
+ "train_samples_per_second": 9.183,
75
+ "train_steps_per_second": 0.024
76
+ }
77
+ ],
78
+ "logging_steps": 10,
79
+ "max_steps": 10,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 5,
82
+ "save_steps": 500,
83
+ "stateful_callbacks": {
84
+ "TrainerControl": {
85
+ "args": {
86
+ "should_epoch_stop": false,
87
+ "should_evaluate": false,
88
+ "should_log": false,
89
+ "should_save": true,
90
+ "should_training_stop": true
91
+ },
92
+ "attributes": {}
93
+ }
94
+ },
95
+ "total_flos": 2.4906238324113408e+17,
96
+ "train_batch_size": 192,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }