Hugging Face's logo

Samuael
/
asr-alffamharic-phoneme-based

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
Samuael commited on
Commit
5633451
•
1 Parent(s): c328c94

End of training

Browse files
Files changed (13) hide show
  1. README.md +42 -11
  2. config.json +1 -1
  3. model.safetensors +3 -0
  4. runs/Nov18_11-06-03_924e25b6928f/events.out.tfevents.1700306032.924e25b6928f.1182.0 +3 -0
  5. runs/Oct20_18-29-03_6c6034ea1465/events.out.tfevents.1697826799.6c6034ea1465.1349.0 +3 -0
  6. runs/Oct20_19-18-09_45f5d4dfe79c/events.out.tfevents.1697829758.45f5d4dfe79c.2866.0 +3 -0
  7. runs/Oct21_06-45-47_39bdfdd087f4/events.out.tfevents.1697870998.39bdfdd087f4.1812.0 +3 -0
  8. runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697879034.f0219920f9f5.329.0 +3 -0
  9. runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697888640.f0219920f9f5.329.1 +3 -0
  10. runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697889426.f0219920f9f5.329.2 +3 -0
  11. runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697890793.f0219920f9f5.329.3 +3 -0
  12. runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697891873.f0219920f9f5.329.4 +3 -0
  13. training_args.bin +2 -2
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Samuael/asr-alffamharic-phoneme-based](https://huggingface.co/Samuael/asr-alffamharic-phoneme-based) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3420
21
- - Wer: 0.4614
22
 
23
  ## Model description
24
 
@@ -37,27 +37,58 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.05
41
- - train_batch_size: 64
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
- - num_epochs: 1
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
- | 0.2647 | 0.26 | 40 | 0.3420 | 0.4607 |
54
- | 0.2841 | 0.52 | 80 | 0.3420 | 0.4603 |
55
- | 0.2698 | 0.78 | 120 | 0.3420 | 0.4614 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
59
 
60
- - Transformers 4.34.1
61
  - Pytorch 2.1.0+cu118
62
- - Datasets 2.14.5
63
- - Tokenizers 0.14.1
 
17
 
18
  This model is a fine-tuned version of [Samuael/asr-alffamharic-phoneme-based](https://huggingface.co/Samuael/asr-alffamharic-phoneme-based) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4498
21
+ - Wer: 0.1084
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
+ - train_batch_size: 32
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
+ - num_epochs: 20
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 1.2273 | 0.59 | 200 | 1.0408 | 0.3569 |
54
+ | 0.7702 | 1.18 | 400 | 0.8009 | 0.2169 |
55
+ | 0.6769 | 1.76 | 600 | 0.6978 | 0.1869 |
56
+ | 0.5454 | 2.35 | 800 | 0.6163 | 0.1696 |
57
+ | 0.5779 | 2.94 | 1000 | 0.5616 | 0.1554 |
58
+ | 0.4996 | 3.53 | 1200 | 0.5413 | 0.1437 |
59
+ | 0.5648 | 4.12 | 1400 | 0.5111 | 0.1439 |
60
+ | 0.4741 | 4.71 | 1600 | 0.5178 | 0.1371 |
61
+ | 0.499 | 5.29 | 1800 | 0.4943 | 0.1324 |
62
+ | 0.4247 | 5.88 | 2000 | 0.4884 | 0.1279 |
63
+ | 0.4008 | 6.47 | 2200 | 0.4667 | 0.1254 |
64
+ | 0.2744 | 7.06 | 2400 | 0.4626 | 0.1288 |
65
+ | 0.3495 | 7.65 | 2600 | 0.4794 | 0.1229 |
66
+ | 0.4016 | 8.24 | 2800 | 0.4548 | 0.1228 |
67
+ | 0.3833 | 8.82 | 3000 | 0.4660 | 0.1209 |
68
+ | 0.3684 | 9.41 | 3200 | 0.4463 | 0.1235 |
69
+ | 0.4149 | 10.0 | 3400 | 0.4697 | 0.1171 |
70
+ | 0.3917 | 10.59 | 3600 | 0.4570 | 0.1188 |
71
+ | 0.2957 | 11.18 | 3800 | 0.4431 | 0.1171 |
72
+ | 0.3054 | 11.76 | 4000 | 0.4530 | 0.1163 |
73
+ | 0.2755 | 12.35 | 4200 | 0.4690 | 0.1138 |
74
+ | 0.3091 | 12.94 | 4400 | 0.4551 | 0.1157 |
75
+ | 0.2617 | 13.53 | 4600 | 0.4557 | 0.1147 |
76
+ | 0.2725 | 14.12 | 4800 | 0.4670 | 0.1088 |
77
+ | 0.2795 | 14.71 | 5000 | 0.4486 | 0.1118 |
78
+ | 0.3493 | 15.29 | 5200 | 0.4471 | 0.1109 |
79
+ | 0.2949 | 15.88 | 5400 | 0.4469 | 0.1090 |
80
+ | 0.2802 | 16.47 | 5600 | 0.4516 | 0.1100 |
81
+ | 0.2655 | 17.06 | 5800 | 0.4418 | 0.1105 |
82
+ | 0.3211 | 17.65 | 6000 | 0.4351 | 0.1095 |
83
+ | 0.2245 | 18.24 | 6200 | 0.4436 | 0.1093 |
84
+ | 0.2244 | 18.82 | 6400 | 0.4493 | 0.1091 |
85
+ | 0.2549 | 19.41 | 6600 | 0.4502 | 0.1082 |
86
+ | 0.3528 | 20.0 | 6800 | 0.4498 | 0.1084 |
87
 
88
 
89
  ### Framework versions
90
 
91
+ - Transformers 4.35.2
92
  - Pytorch 2.1.0+cu118
93
+ - Datasets 2.15.0
94
+ - Tokenizers 0.15.0
config.json CHANGED
@@ -111,7 +111,7 @@
111
  1
112
  ],
113
  "torch_dtype": "float32",
114
- "transformers_version": "4.34.1",
115
  "use_weighted_layer_sum": false,
116
  "vocab_size": 41,
117
  "xvector_output_dim": 512
 
111
  1
112
  ],
113
  "torch_dtype": "float32",
114
+ "transformers_version": "4.35.2",
115
  "use_weighted_layer_sum": false,
116
  "vocab_size": 41,
117
  "xvector_output_dim": 512
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a18d6e47fa23f3d79dbd3a15f2e2e562311498cb4e428f7fad9c84c6d5823e02
3
+ size 377638812
runs/Nov18_11-06-03_924e25b6928f/events.out.tfevents.1700306032.924e25b6928f.1182.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54407230103aef0881853370069396b7fa1e316a17c82aacebd5109bff3dd590
3
+ size 550875
runs/Oct20_18-29-03_6c6034ea1465/events.out.tfevents.1697826799.6c6034ea1465.1349.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeeaeb19db82f966c5ef70097ac6bc1850a496ac5f5137fecf9fe8e5762fcec8
3
+ size 86237
runs/Oct20_19-18-09_45f5d4dfe79c/events.out.tfevents.1697829758.45f5d4dfe79c.2866.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ede00a5f1716764bd2b641956087e0ad4071bc1813f11040cea4d39ae16ea71
3
+ size 13260
runs/Oct21_06-45-47_39bdfdd087f4/events.out.tfevents.1697870998.39bdfdd087f4.1812.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7acdf204d7eaaef9ee4d8b94bfc78213690186aae2a512d0c4690b48d192e8fe
3
+ size 267185
runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697879034.f0219920f9f5.329.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a965ba31e432635d4defcee648de942099ea453043550b200be448a469bcb8
3
+ size 398245
runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697888640.f0219920f9f5.329.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e96f24b9fe94bee77eba962e3b49d74ebc75062a00dfb2d19153d463008e7c0
3
+ size 30525
runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697889426.f0219920f9f5.329.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d276e981b2d5f80ed1f2ce76bf05c622056efac632de6c8985dd28c3dcfea4e
3
+ size 32413
runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697890793.f0219920f9f5.329.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:426f964307d5f4af0b7505457f3c0db8ac9418614ebe65a6a5308c22e57fa0f5
3
+ size 32413
runs/Oct21_09-00-37_f0219920f9f5/events.out.tfevents.1697891873.f0219920f9f5.329.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82d62fdbb70299c5089b372c0c1e73c95f8187cf579275e99e18b87e89165b44
3
+ size 19051
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cff90c35cc6bd331f70b407ab593e64509b7eb3f2926db4adfafbcf4609454b
3
- size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19dd352422ce115d747eda938f76b716d06b52983ac10ede089607f80e836897
3
+ size 4664