Bakhtiar56 commited on
Commit
81f217b
1 Parent(s): f73658a

End of training

Browse files
README.md CHANGED
@@ -3,6 +3,8 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: facebook/wav2vec2-large-xlsr-53
5
  tags:
 
 
6
  - generated_from_trainer
7
  datasets:
8
  - fleurs
@@ -15,15 +17,15 @@ model-index:
15
  name: Automatic Speech Recognition
16
  type: automatic-speech-recognition
17
  dataset:
18
- name: fleurs
19
  type: fleurs
20
  config: en_us
21
  split: test
22
- args: en_us
23
  metrics:
24
  - name: Wer
25
  type: wer
26
- value: 0.260403073800203
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # wav2vec2-common_voice-en-finetune
33
 
34
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the fleurs dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.3437
37
- - Wer: 0.2604
38
 
39
  ## Model description
40
 
 
3
  license: apache-2.0
4
  base_model: facebook/wav2vec2-large-xlsr-53
5
  tags:
6
+ - automatic-speech-recognition
7
+ - google/fleurs
8
  - generated_from_trainer
9
  datasets:
10
  - fleurs
 
17
  name: Automatic Speech Recognition
18
  type: automatic-speech-recognition
19
  dataset:
20
+ name: GOOGLE/FLEURS - EN_US
21
  type: fleurs
22
  config: en_us
23
  split: test
24
+ args: 'Config: en_us, Training split: train+validation, Eval split: test'
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 0.25982311149775267
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  # wav2vec2-common_voice-en-finetune
35
 
36
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the GOOGLE/FLEURS - EN_US dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.3436
39
+ - Wer: 0.2598
40
 
41
  ## Model description
42
 
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_loss": 0.3435712456703186,
4
+ "eval_runtime": 35.2885,
5
+ "eval_samples": 637,
6
+ "eval_samples_per_second": 18.051,
7
+ "eval_steps_per_second": 2.267,
8
+ "eval_wer": 0.25982311149775267,
9
+ "total_flos": 9.080032524835507e+18,
10
+ "train_loss": 2.111865760969079,
11
+ "train_runtime": 3049.4338,
12
+ "train_samples": 2938,
13
+ "train_samples_per_second": 9.635,
14
+ "train_steps_per_second": 0.302
15
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_loss": 0.3435712456703186,
4
+ "eval_runtime": 35.2885,
5
+ "eval_samples": 637,
6
+ "eval_samples_per_second": 18.051,
7
+ "eval_steps_per_second": 2.267,
8
+ "eval_wer": 0.25982311149775267
9
+ }
runs/Sep07_10-42-27_nvidia-gpu-machine/events.out.tfevents.1725701758.nvidia-gpu-machine ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6ff96cb232f0e3f90083dc12fe26127dc12155986d7de61cf9fec897ec111d
3
+ size 40
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 9.080032524835507e+18,
4
+ "train_loss": 2.111865760969079,
5
+ "train_runtime": 3049.4338,
6
+ "train_samples": 2938,
7
+ "train_samples_per_second": 9.635,
8
+ "train_steps_per_second": 0.302
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 100,
6
+ "global_step": 920,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0869565217391304,
13
+ "eval_loss": 3.51055908203125,
14
+ "eval_runtime": 36.2042,
15
+ "eval_samples_per_second": 17.595,
16
+ "eval_steps_per_second": 2.21,
17
+ "eval_wer": 1.0,
18
+ "step": 100
19
+ },
20
+ {
21
+ "epoch": 2.1739130434782608,
22
+ "eval_loss": 2.9226224422454834,
23
+ "eval_runtime": 35.9506,
24
+ "eval_samples_per_second": 17.719,
25
+ "eval_steps_per_second": 2.225,
26
+ "eval_wer": 1.0,
27
+ "step": 200
28
+ },
29
+ {
30
+ "epoch": 3.260869565217391,
31
+ "eval_loss": 2.874464988708496,
32
+ "eval_runtime": 35.9419,
33
+ "eval_samples_per_second": 17.723,
34
+ "eval_steps_per_second": 2.226,
35
+ "eval_wer": 1.0,
36
+ "step": 300
37
+ },
38
+ {
39
+ "epoch": 4.3478260869565215,
40
+ "eval_loss": 1.8099528551101685,
41
+ "eval_runtime": 35.9111,
42
+ "eval_samples_per_second": 17.738,
43
+ "eval_steps_per_second": 2.228,
44
+ "eval_wer": 0.9803537770044947,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 5.434782608695652,
49
+ "grad_norm": 0.6213024258613586,
50
+ "learning_rate": 0.0002988,
51
+ "loss": 3.7609,
52
+ "step": 500
53
+ },
54
+ {
55
+ "epoch": 5.434782608695652,
56
+ "eval_loss": 0.4771381616592407,
57
+ "eval_runtime": 35.9706,
58
+ "eval_samples_per_second": 17.709,
59
+ "eval_steps_per_second": 2.224,
60
+ "eval_wer": 0.4206901551399159,
61
+ "step": 500
62
+ },
63
+ {
64
+ "epoch": 6.521739130434782,
65
+ "eval_loss": 0.3808304965496063,
66
+ "eval_runtime": 36.4619,
67
+ "eval_samples_per_second": 17.47,
68
+ "eval_steps_per_second": 2.194,
69
+ "eval_wer": 0.34841235319704217,
70
+ "step": 600
71
+ },
72
+ {
73
+ "epoch": 7.608695652173913,
74
+ "eval_loss": 0.34075430035591125,
75
+ "eval_runtime": 35.8567,
76
+ "eval_samples_per_second": 17.765,
77
+ "eval_steps_per_second": 2.231,
78
+ "eval_wer": 0.28715383500072494,
79
+ "step": 700
80
+ },
81
+ {
82
+ "epoch": 8.695652173913043,
83
+ "eval_loss": 0.3479066789150238,
84
+ "eval_runtime": 35.8444,
85
+ "eval_samples_per_second": 17.771,
86
+ "eval_steps_per_second": 2.232,
87
+ "eval_wer": 0.2719298245614035,
88
+ "step": 800
89
+ },
90
+ {
91
+ "epoch": 9.782608695652174,
92
+ "eval_loss": 0.3436548411846161,
93
+ "eval_runtime": 35.796,
94
+ "eval_samples_per_second": 17.795,
95
+ "eval_steps_per_second": 2.235,
96
+ "eval_wer": 0.260403073800203,
97
+ "step": 900
98
+ },
99
+ {
100
+ "epoch": 10.0,
101
+ "step": 920,
102
+ "total_flos": 9.080032524835507e+18,
103
+ "train_loss": 2.111865760969079,
104
+ "train_runtime": 3049.4338,
105
+ "train_samples_per_second": 9.635,
106
+ "train_steps_per_second": 0.302
107
+ }
108
+ ],
109
+ "logging_steps": 500,
110
+ "max_steps": 920,
111
+ "num_input_tokens_seen": 0,
112
+ "num_train_epochs": 10,
113
+ "save_steps": 400,
114
+ "stateful_callbacks": {
115
+ "TrainerControl": {
116
+ "args": {
117
+ "should_epoch_stop": false,
118
+ "should_evaluate": false,
119
+ "should_log": false,
120
+ "should_save": true,
121
+ "should_training_stop": true
122
+ },
123
+ "attributes": {}
124
+ }
125
+ },
126
+ "total_flos": 9.080032524835507e+18,
127
+ "train_batch_size": 16,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }