End of training
Browse files
README.md
CHANGED
@@ -1,18 +1,18 @@
|
|
1 |
---
|
|
|
2 |
base_model: facebook/wav2vec2-base
|
|
|
|
|
3 |
datasets:
|
4 |
- common_voice_13_0
|
5 |
-
license: apache-2.0
|
6 |
metrics:
|
7 |
- wer
|
8 |
-
tags:
|
9 |
-
- generated_from_trainer
|
10 |
model-index:
|
11 |
- name: wav2vec2-large-xls-r-vi-colab
|
12 |
results:
|
13 |
- task:
|
14 |
-
type: automatic-speech-recognition
|
15 |
name: Automatic Speech Recognition
|
|
|
16 |
dataset:
|
17 |
name: common_voice_13_0
|
18 |
type: common_voice_13_0
|
@@ -20,9 +20,9 @@ model-index:
|
|
20 |
split: test[:50%]
|
21 |
args: vi
|
22 |
metrics:
|
23 |
-
-
|
24 |
-
|
25 |
-
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the common_voice_13_0 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Wer: 0
|
37 |
-
- Cer: 0
|
38 |
|
39 |
## Model description
|
40 |
|
@@ -53,28 +53,33 @@ More information needed
|
|
53 |
### Training hyperparameters
|
54 |
|
55 |
The following hyperparameters were used during training:
|
56 |
-
- learning_rate:
|
57 |
-
- train_batch_size:
|
58 |
- eval_batch_size: 8
|
59 |
- seed: 42
|
60 |
- gradient_accumulation_steps: 2
|
61 |
-
- total_train_batch_size:
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
-
- lr_scheduler_warmup_steps:
|
65 |
-
- num_epochs:
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
71 |
-
|
72 |
-
|
|
73 |
-
|
|
74 |
-
| 3.
|
75 |
-
| 3.
|
76 |
-
|
|
77 |
-
|
|
|
|
|
|
|
|
|
|
|
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice_13_0
|
|
|
8 |
metrics:
|
9 |
- wer
|
|
|
|
|
10 |
model-index:
|
11 |
- name: wav2vec2-large-xls-r-vi-colab
|
12 |
results:
|
13 |
- task:
|
|
|
14 |
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
dataset:
|
17 |
name: common_voice_13_0
|
18 |
type: common_voice_13_0
|
|
|
20 |
split: test[:50%]
|
21 |
args: vi
|
22 |
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 1.0
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the common_voice_13_0 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 3.4884
|
36 |
+
- Wer: 1.0
|
37 |
+
- Cer: 1.0
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
53 |
### Training hyperparameters
|
54 |
|
55 |
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 1e-05
|
57 |
+
- train_batch_size: 32
|
58 |
- eval_batch_size: 8
|
59 |
- seed: 42
|
60 |
- gradient_accumulation_steps: 2
|
61 |
+
- total_train_batch_size: 64
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
+
- lr_scheduler_warmup_steps: 0.1
|
65 |
+
- num_epochs: 80
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
71 |
+
|:-------------:|:-------:|:----:|:---------------:|:---:|:---:|
|
72 |
+
| 9.4752 | 7.1111 | 160 | 4.4992 | 1.0 | 1.0 |
|
73 |
+
| 4.2035 | 14.2222 | 320 | 3.9228 | 1.0 | 1.0 |
|
74 |
+
| 3.7611 | 21.3333 | 480 | 3.6584 | 1.0 | 1.0 |
|
75 |
+
| 3.5825 | 28.4444 | 640 | 3.5584 | 1.0 | 1.0 |
|
76 |
+
| 3.5044 | 35.5556 | 800 | 3.5285 | 1.0 | 1.0 |
|
77 |
+
| 3.4669 | 42.6667 | 960 | 3.5226 | 1.0 | 1.0 |
|
78 |
+
| 3.4382 | 49.7778 | 1120 | 3.5093 | 1.0 | 1.0 |
|
79 |
+
| 3.4183 | 56.8889 | 1280 | 3.4942 | 1.0 | 1.0 |
|
80 |
+
| 3.4002 | 64.0 | 1440 | 3.4957 | 1.0 | 1.0 |
|
81 |
+
| 3.3871 | 71.1111 | 1600 | 3.4896 | 1.0 | 1.0 |
|
82 |
+
| 3.382 | 78.2222 | 1760 | 3.4884 | 1.0 | 1.0 |
|
83 |
|
84 |
|
85 |
### Framework versions
|