Hugging Face's logo

Samuael
/
asr-amharic-phoneme-based-37-6

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Samuael commited on
Commit
6d40efb
•
1 Parent(s): dac2374

End of training

Browse files
Files changed (7) hide show
  1. README.md +54 -12
  2. config.json +1 -1
  3. model.safetensors +2 -2
  4. runs/Jan27_13-06-13_c2c77f5c73da/events.out.tfevents.1706360803.c2c77f5c73da.200.0 +3 -0
  5. runs/Jan27_13-45-02_fa652a3bb7a9/events.out.tfevents.1706364243.fa652a3bb7a9.268.0 +3 -0
  6. runs/Jan27_15-16-19_200cf53425ee/events.out.tfevents.1706369632.200cf53425ee.901.0 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,10 @@
1
  ---
2
  license: apache-2.0
3
- base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: asr-amharic-phoneme-based-37-6
8
  results: []
@@ -13,17 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # asr-amharic-phoneme-based-37-6
15
 
16
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 0.2492
19
- - eval_wer: 0.2974
20
- - eval_phoneme_cer: 0.0554
21
- - eval_cer: 0.0798
22
- - eval_runtime: 24.1249
23
- - eval_samples_per_second: 14.881
24
- - eval_steps_per_second: 1.865
25
- - epoch: 46.37
26
- - step: 37000
27
 
28
  ## Model description
29
 
@@ -49,7 +46,52 @@ The following hyperparameters were used during training:
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_steps: 100
52
- - num_epochs: 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
  ### Framework versions
55
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: Samuael/asr-amharic-phoneme-based-37-6
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: asr-amharic-phoneme-based-37-6
10
  results: []
 
15
 
16
  # asr-amharic-phoneme-based-37-6
17
 
18
+ This model is a fine-tuned version of [Samuael/asr-amharic-phoneme-based-37-6](https://huggingface.co/Samuael/asr-amharic-phoneme-based-37-6) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.2467
21
+ - Wer: 0.2877
22
+ - Phoneme Cer: 0.0539
23
+ - Cer: 0.0777
 
 
 
 
 
24
 
25
  ## Model description
26
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 100
49
+ - num_epochs: 10
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Phoneme Cer | Cer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:------:|
55
+ | 3.2186 | 0.25 | 200 | 3.2626 | 1.0 | 1.0 | 1.0 |
56
+ | 3.0459 | 0.5 | 400 | 3.0440 | 1.0 | 1.0 | 1.0 |
57
+ | 2.9983 | 0.75 | 600 | 2.9807 | 1.0 | 1.0 | 1.0 |
58
+ | 1.8006 | 1.0 | 800 | 1.4020 | 0.8218 | 0.2751 | 0.4270 |
59
+ | 0.6145 | 1.25 | 1000 | 0.4420 | 0.3611 | 0.0717 | 0.1040 |
60
+ | 0.4288 | 1.5 | 1200 | 0.3304 | 0.3394 | 0.0649 | 0.0941 |
61
+ | 0.3335 | 1.75 | 1400 | 0.2996 | 0.3314 | 0.0622 | 0.0909 |
62
+ | 0.4583 | 2.01 | 1600 | 0.2815 | 0.3263 | 0.0612 | 0.0890 |
63
+ | 0.3966 | 2.26 | 1800 | 0.2743 | 0.3120 | 0.0584 | 0.0847 |
64
+ | 0.3781 | 2.51 | 2000 | 0.2669 | 0.3241 | 0.0609 | 0.0881 |
65
+ | 0.5792 | 2.76 | 2200 | 0.2597 | 0.3135 | 0.0590 | 0.0857 |
66
+ | 0.3322 | 3.01 | 2400 | 0.2548 | 0.3076 | 0.0575 | 0.0837 |
67
+ | 0.4129 | 3.26 | 2600 | 0.2577 | 0.3051 | 0.0575 | 0.0832 |
68
+ | 0.3453 | 3.51 | 2800 | 0.2520 | 0.3070 | 0.0577 | 0.0828 |
69
+ | 0.3279 | 3.76 | 3000 | 0.2516 | 0.2989 | 0.0563 | 0.0818 |
70
+ | 0.3312 | 4.01 | 3200 | 0.2487 | 0.2947 | 0.0553 | 0.0801 |
71
+ | 0.2818 | 4.26 | 3400 | 0.2530 | 0.2985 | 0.0563 | 0.0816 |
72
+ | 0.2244 | 4.51 | 3600 | 0.2529 | 0.3021 | 0.0565 | 0.0820 |
73
+ | 0.3562 | 4.76 | 3800 | 0.2477 | 0.2984 | 0.0563 | 0.0814 |
74
+ | 0.2922 | 5.01 | 4000 | 0.2530 | 0.2995 | 0.0563 | 0.0813 |
75
+ | 0.2535 | 5.26 | 4200 | 0.2516 | 0.2990 | 0.0556 | 0.0805 |
76
+ | 0.2043 | 5.51 | 4400 | 0.2532 | 0.2966 | 0.0557 | 0.0800 |
77
+ | 0.2653 | 5.76 | 4600 | 0.2471 | 0.2922 | 0.0548 | 0.0792 |
78
+ | 0.4389 | 6.02 | 4800 | 0.2493 | 0.2942 | 0.0555 | 0.0805 |
79
+ | 0.2757 | 6.27 | 5000 | 0.2533 | 0.2928 | 0.0551 | 0.0799 |
80
+ | 0.3063 | 6.52 | 5200 | 0.2459 | 0.2950 | 0.0554 | 0.0800 |
81
+ | 0.2069 | 6.77 | 5400 | 0.2499 | 0.2946 | 0.0555 | 0.0800 |
82
+ | 0.2018 | 7.02 | 5600 | 0.2503 | 0.2934 | 0.0549 | 0.0792 |
83
+ | 0.2068 | 7.27 | 5800 | 0.2469 | 0.2966 | 0.0551 | 0.0798 |
84
+ | 0.2535 | 7.52 | 6000 | 0.2513 | 0.2936 | 0.0548 | 0.0792 |
85
+ | 0.285 | 7.77 | 6200 | 0.2492 | 0.2941 | 0.0548 | 0.0795 |
86
+ | 0.1801 | 8.02 | 6400 | 0.2460 | 0.2896 | 0.0540 | 0.0781 |
87
+ | 0.1705 | 8.27 | 6600 | 0.2475 | 0.2933 | 0.0549 | 0.0793 |
88
+ | 0.3344 | 8.52 | 6800 | 0.2501 | 0.2890 | 0.0540 | 0.0777 |
89
+ | 0.2236 | 8.77 | 7000 | 0.2471 | 0.2871 | 0.0536 | 0.0773 |
90
+ | 0.349 | 9.02 | 7200 | 0.2480 | 0.2869 | 0.0541 | 0.0779 |
91
+ | 0.2692 | 9.27 | 7400 | 0.2482 | 0.2891 | 0.0540 | 0.0779 |
92
+ | 0.2265 | 9.52 | 7600 | 0.2481 | 0.2879 | 0.0539 | 0.0776 |
93
+ | 0.1649 | 9.77 | 7800 | 0.2467 | 0.2877 | 0.0539 | 0.0777 |
94
+
95
 
96
  ### Framework versions
97
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
3
  "activation_dropout": 0.0,
4
  "adapter_attn_dim": null,
5
  "adapter_kernel_size": 3,
 
1
  {
2
+ "_name_or_path": "Samuael/asr-amharic-phoneme-based-37-6",
3
  "activation_dropout": 0.0,
4
  "adapter_attn_dim": null,
5
  "adapter_kernel_size": 3,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71b4857f31d60f2e6f2038c603478286ba3c71efd6142ca42bca5d0f4b212551
3
- size 1272092364
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc126cf9cf72125ac04699bde1d26c37ad12700c31dc24d1c532900e6b84be61
3
+ size 1261959180
runs/Jan27_13-06-13_c2c77f5c73da/events.out.tfevents.1706360803.c2c77f5c73da.200.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9607dcd4c5f7e375ae58ce055277218d3200084aa3a75b727cbd1e8f2aa6fb6
3
+ size 10260
runs/Jan27_13-45-02_fa652a3bb7a9/events.out.tfevents.1706364243.fa652a3bb7a9.268.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b0ecb9c0d53732ddff7500ac22aea81bd675501b4b3a39e1cdd1e79748c897
3
+ size 6062
runs/Jan27_15-16-19_200cf53425ee/events.out.tfevents.1706369632.200cf53425ee.901.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e18005e4ffc2e32315fcb27d252f380764547192eb7157e844becefd889b30
3
+ size 649037
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:681029fd95f8a4a81bdf5fb325ecfbe2951768408cdfab396732daa70c8ad94b
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc7f743053e7ec0ae929f3e3dd91265d23ea91ed9a8fae564beac8dd0015e3e
3
  size 4664