Hugging Face's logo

nrshoudi
/
hubert_arabic_mdd

Automatic Speech Recognition
Transformers
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Community
nrshoudi commited on
Commit
a5889ea
•
1 Parent(s): 7f93eff

End of training

Browse files
Files changed (4) hide show
  1. README.md +23 -23
  2. model.safetensors +1 -1
  3. preprocessor_config.json +0 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3991
21
- - Wer: 0.0466
22
- - Per: 0.0363
23
 
24
  ## Model description
25
 
@@ -51,26 +51,26 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer | Per |
53
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
54
- | 5.6351 | 1.0 | 1637 | 0.7704 | 0.3277 | 0.3110 |
55
- | 0.3646 | 2.0 | 3274 | 0.4333 | 0.0673 | 0.0540 |
56
- | 0.1587 | 3.0 | 4911 | 0.3876 | 0.0710 | 0.0580 |
57
- | 0.1105 | 4.0 | 6548 | 0.3608 | 0.0670 | 0.0558 |
58
- | 0.0878 | 5.0 | 8185 | 0.3808 | 0.0678 | 0.0562 |
59
- | 0.0738 | 6.0 | 9822 | 0.3576 | 0.0639 | 0.0518 |
60
- | 0.0594 | 7.0 | 11459 | 0.3309 | 0.0617 | 0.0508 |
61
- | 0.056 | 8.0 | 13096 | 0.3570 | 0.0587 | 0.0467 |
62
- | 0.0478 | 9.0 | 14733 | 0.3450 | 0.0583 | 0.0473 |
63
- | 0.0388 | 10.0 | 16370 | 0.3993 | 0.0591 | 0.0480 |
64
- | 0.0378 | 11.0 | 18007 | 0.4172 | 0.0550 | 0.0437 |
65
- | 0.0319 | 12.0 | 19644 | 0.3625 | 0.0518 | 0.0413 |
66
- | 0.0309 | 13.0 | 21281 | 0.3794 | 0.0505 | 0.0392 |
67
- | 0.0257 | 14.0 | 22918 | 0.3897 | 0.0534 | 0.0426 |
68
- | 0.0202 | 15.0 | 24555 | 0.4077 | 0.0512 | 0.0404 |
69
- | 0.0197 | 16.0 | 26192 | 0.3846 | 0.0508 | 0.0411 |
70
- | 0.016 | 17.0 | 27829 | 0.3808 | 0.0491 | 0.0391 |
71
- | 0.0157 | 18.0 | 29466 | 0.4060 | 0.0471 | 0.0373 |
72
- | 0.0131 | 19.0 | 31103 | 0.3925 | 0.0465 | 0.0361 |
73
- | 0.0115 | 20.0 | 32740 | 0.3991 | 0.0466 | 0.0363 |
74
 
75
 
76
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5363
21
+ - Wer: 0.0490
22
+ - Per: 0.0376
23
 
24
  ## Model description
25
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer | Per |
53
  |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
54
+ | 2.371 | 1.0 | 818 | 1.3106 | 0.6828 | 0.6863 |
55
+ | 0.9013 | 2.0 | 1636 | 0.4890 | 0.1144 | 0.0985 |
56
+ | 0.3369 | 3.0 | 2454 | 0.4295 | 0.0766 | 0.0611 |
57
+ | 0.2219 | 4.0 | 3272 | 0.4386 | 0.0649 | 0.0508 |
58
+ | 0.1565 | 5.0 | 4090 | 0.4124 | 0.0660 | 0.0506 |
59
+ | 0.1343 | 6.0 | 4908 | 0.4422 | 0.0630 | 0.0493 |
60
+ | 0.106 | 7.0 | 5726 | 0.4762 | 0.0600 | 0.0469 |
61
+ | 0.091 | 8.0 | 6544 | 0.4487 | 0.0580 | 0.0460 |
62
+ | 0.0745 | 9.0 | 7362 | 0.4284 | 0.0577 | 0.0461 |
63
+ | 0.0708 | 10.0 | 8180 | 0.4161 | 0.0578 | 0.0451 |
64
+ | 0.0621 | 11.0 | 8998 | 0.4659 | 0.0535 | 0.0414 |
65
+ | 0.0492 | 12.0 | 9816 | 0.5249 | 0.0557 | 0.0433 |
66
+ | 0.0479 | 13.0 | 10634 | 0.5411 | 0.0550 | 0.0426 |
67
+ | 0.0452 | 14.0 | 11452 | 0.5161 | 0.0536 | 0.0410 |
68
+ | 0.0385 | 15.0 | 12270 | 0.5002 | 0.0521 | 0.0404 |
69
+ | 0.0354 | 16.0 | 13088 | 0.4800 | 0.0499 | 0.0389 |
70
+ | 0.0342 | 17.0 | 13906 | 0.5079 | 0.0506 | 0.0394 |
71
+ | 0.0269 | 18.0 | 14724 | 0.5144 | 0.0499 | 0.0386 |
72
+ | 0.0247 | 19.0 | 15542 | 0.5334 | 0.0496 | 0.0380 |
73
+ | 0.0208 | 20.0 | 16360 | 0.5363 | 0.0490 | 0.0376 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2969a7623859b9a904b126801a107448526dca244893252958260ce5f33819ac
3
  size 1261970648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4ee4d3ca9b243c6128b6a6c9f7523ed0cf56de4ea07373696d9055a09398d6
3
  size 1261970648
preprocessor_config.json CHANGED
@@ -4,7 +4,6 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0,
7
- "processor_class": "Wav2Vec2Processor",
8
  "return_attention_mask": true,
9
  "sampling_rate": 16000
10
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0,
 
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3a1aeff00b8bc3228970214b85879c5999771d34eb110131836d18ee1b0b128
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdcbf3563aa16d993b17cc9be35f2c9bdcd5010b0dd9cbbb8f117910c99e21dd
3
  size 4600