kiranpantha
commited on
Commit
•
85af3fc
1
Parent(s):
ecec38d
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
language:
|
4 |
+
- ne
|
5 |
+
license: mit
|
6 |
+
base_model: kiranpantha/w2v-bert-2.0-nepali-iteration-test
|
7 |
+
tags:
|
8 |
+
- generated_from_trainer
|
9 |
+
datasets:
|
10 |
+
- kiranpantha/OpenSLR54-Balanced-Nepali
|
11 |
+
metrics:
|
12 |
+
- wer
|
13 |
+
model-index:
|
14 |
+
- name: Wave2Vec2-Bert2.0 - Kiran Pantha
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Automatic Speech Recognition
|
18 |
+
type: automatic-speech-recognition
|
19 |
+
dataset:
|
20 |
+
name: OpenSLR54
|
21 |
+
type: kiranpantha/OpenSLR54-Balanced-Nepali
|
22 |
+
config: default
|
23 |
+
split: test
|
24 |
+
args: 'config: ne, split: train,test'
|
25 |
+
metrics:
|
26 |
+
- name: Wer
|
27 |
+
type: wer
|
28 |
+
value: 0.4636116306750553
|
29 |
+
---
|
30 |
+
|
31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
+
should probably proofread and complete it, then remove this comment. -->
|
33 |
+
|
34 |
+
# Wave2Vec2-Bert2.0 - Kiran Pantha
|
35 |
+
|
36 |
+
This model is a fine-tuned version of [kiranpantha/w2v-bert-2.0-nepali-iteration-test](https://huggingface.co/kiranpantha/w2v-bert-2.0-nepali-iteration-test) on the OpenSLR54 dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.4545
|
39 |
+
- Wer: 0.4636
|
40 |
+
|
41 |
+
## Model description
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Intended uses & limitations
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training and evaluation data
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Training procedure
|
54 |
+
|
55 |
+
### Training hyperparameters
|
56 |
+
|
57 |
+
The following hyperparameters were used during training:
|
58 |
+
- learning_rate: 5e-05
|
59 |
+
- train_batch_size: 8
|
60 |
+
- eval_batch_size: 8
|
61 |
+
- seed: 42
|
62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
+
- lr_scheduler_type: linear
|
64 |
+
- lr_scheduler_warmup_steps: 500
|
65 |
+
- num_epochs: 2
|
66 |
+
- mixed_precision_training: Native AMP
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
72 |
+
| 0.392 | 0.15 | 300 | 0.4561 | 0.4579 |
|
73 |
+
| 0.5077 | 0.3 | 600 | 0.5402 | 0.5145 |
|
74 |
+
| 0.5371 | 0.45 | 900 | 0.5083 | 0.4923 |
|
75 |
+
| 0.4943 | 0.6 | 1200 | 0.5103 | 0.5147 |
|
76 |
+
| 0.5049 | 0.75 | 1500 | 0.4811 | 0.4752 |
|
77 |
+
| 0.4809 | 0.9 | 1800 | 0.4751 | 0.4689 |
|
78 |
+
| 0.4633 | 1.05 | 2100 | 0.5031 | 0.4883 |
|
79 |
+
| 0.3843 | 1.2 | 2400 | 0.4703 | 0.4573 |
|
80 |
+
| 0.3753 | 1.35 | 2700 | 0.4542 | 0.4497 |
|
81 |
+
| 0.356 | 1.5 | 3000 | 0.4510 | 0.4503 |
|
82 |
+
| 0.3668 | 1.65 | 3300 | 0.4591 | 0.4524 |
|
83 |
+
| 0.3386 | 1.8 | 3600 | 0.4399 | 0.4459 |
|
84 |
+
| 0.3452 | 1.95 | 3900 | 0.4545 | 0.4636 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.45.0.dev0
|
90 |
+
- Pytorch 2.4.1+cu121
|
91 |
+
- Datasets 2.21.0
|
92 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423081060
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c62996c0dfe57f1e2534293486156ad2feadbb0f39aa19cb50db1ff7e00e1ef
|
3 |
size 2423081060
|
runs/Sep24_21-47-53_kiran/events.out.tfevents.1727193865.kiran.142209.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b56057143308ca0685e4487b56e04f36b8b1e9ed77c6fe5973cca22de93029cf
|
3 |
+
size 13531
|