TheAIchemist13
commited on
Commit
•
2f548cd
1
Parent(s):
17a0b0d
End of training
Browse files- README.md +78 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: Harveenchadha/vakyansh-wav2vec2-hindi-him-4200
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: hindi_wav2vec2_optimized_2
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# hindi_wav2vec2_optimized_2
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [Harveenchadha/vakyansh-wav2vec2-hindi-him-4200](https://huggingface.co/Harveenchadha/vakyansh-wav2vec2-hindi-him-4200) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.4408
|
21 |
+
- Wer: 0.3122
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0003
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 32
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_steps: 10
|
49 |
+
- num_epochs: 100
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
+
| 3.2061 | 5.56 | 25 | 1.5744 | 0.5338 |
|
56 |
+
| 0.4727 | 11.11 | 50 | 1.4735 | 0.4409 |
|
57 |
+
| 0.2901 | 16.67 | 75 | 1.6240 | 0.4536 |
|
58 |
+
| 0.1643 | 22.22 | 100 | 1.4403 | 0.4726 |
|
59 |
+
| 0.0991 | 27.78 | 125 | 1.3516 | 0.4114 |
|
60 |
+
| 0.0512 | 33.33 | 150 | 1.3740 | 0.4409 |
|
61 |
+
| 0.0645 | 38.89 | 175 | 1.3560 | 0.3903 |
|
62 |
+
| 0.0461 | 44.44 | 200 | 1.3505 | 0.3840 |
|
63 |
+
| 0.0372 | 50.0 | 225 | 1.5078 | 0.4114 |
|
64 |
+
| 0.0277 | 55.56 | 250 | 1.5161 | 0.3629 |
|
65 |
+
| 0.0201 | 61.11 | 275 | 1.4834 | 0.3819 |
|
66 |
+
| 0.016 | 66.67 | 300 | 1.4693 | 0.3608 |
|
67 |
+
| 0.0122 | 72.22 | 325 | 1.4352 | 0.3439 |
|
68 |
+
| 0.0147 | 77.78 | 350 | 1.4382 | 0.3291 |
|
69 |
+
| 0.0098 | 83.33 | 375 | 1.4329 | 0.3122 |
|
70 |
+
| 0.015 | 88.89 | 400 | 1.4408 | 0.3122 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.34.0
|
76 |
+
- Pytorch 2.0.1+cu118
|
77 |
+
- Datasets 2.14.5
|
78 |
+
- Tokenizers 0.14.1
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377766433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da63d924c6b6851c8344038432d3e36180b178bf88c65cf3fff6d378b675d1e5
|
3 |
size 377766433
|