Commit
•
ddc6a04
1
Parent(s):
878958a
update model card README.md
Browse files
README.md
CHANGED
@@ -1,27 +1,11 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- common_voice_13_0
|
7 |
-
metrics:
|
8 |
-
- wer
|
9 |
model-index:
|
10 |
- name: wav2vec2-large-xls-r-300m-hindi-colab-ysv
|
11 |
-
results:
|
12 |
-
- task:
|
13 |
-
name: Automatic Speech Recognition
|
14 |
-
type: automatic-speech-recognition
|
15 |
-
dataset:
|
16 |
-
name: common_voice_13_0
|
17 |
-
type: common_voice_13_0
|
18 |
-
config: hi
|
19 |
-
split: test
|
20 |
-
args: hi
|
21 |
-
metrics:
|
22 |
-
- name: Wer
|
23 |
-
type: wer
|
24 |
-
value: 0.8740320510166052
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,10 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# wav2vec2-large-xls-r-300m-hindi-colab-ysv
|
31 |
|
32 |
-
This model
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
-
|
35 |
-
-
|
|
|
|
|
|
|
|
|
|
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -52,22 +41,15 @@ More information needed
|
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 0.0003
|
55 |
-
- train_batch_size:
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
58 |
- gradient_accumulation_steps: 2
|
59 |
-
- total_train_batch_size:
|
60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
- lr_scheduler_type: linear
|
62 |
- lr_scheduler_warmup_steps: 500
|
63 |
-
- num_epochs:
|
64 |
-
|
65 |
-
### Training results
|
66 |
-
|
67 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
-
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
69 |
-
| 5.7147 | 2.86 | 400 | 1.6224 | 0.8740 |
|
70 |
-
|
71 |
|
72 |
### Framework versions
|
73 |
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
datasets:
|
5 |
- common_voice_13_0
|
|
|
|
|
6 |
model-index:
|
7 |
- name: wav2vec2-large-xls-r-300m-hindi-colab-ysv
|
8 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
13 |
|
14 |
# wav2vec2-large-xls-r-300m-hindi-colab-ysv
|
15 |
|
16 |
+
This model was trained from scratch on the common_voice_13_0 dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- eval_loss: 1.1359
|
19 |
+
- eval_wer: 0.5396
|
20 |
+
- eval_runtime: 278.3234
|
21 |
+
- eval_samples_per_second: 10.588
|
22 |
+
- eval_steps_per_second: 1.326
|
23 |
+
- epoch: 18.21
|
24 |
+
- step: 6800
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
- learning_rate: 0.0003
|
44 |
+
- train_batch_size: 6
|
45 |
- eval_batch_size: 8
|
46 |
- seed: 42
|
47 |
- gradient_accumulation_steps: 2
|
48 |
+
- total_train_batch_size: 12
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
- lr_scheduler_warmup_steps: 500
|
52 |
+
- num_epochs: 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
53 |
|
54 |
### Framework versions
|
55 |
|