End of training
Browse files
README.md
CHANGED
@@ -1,13 +1,28 @@
|
|
1 |
---
|
2 |
-
base_model: facebook/wav2vec2-base
|
3 |
license: apache-2.0
|
4 |
-
|
5 |
-
- wer
|
6 |
tags:
|
7 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: wav2vec2-large-xls-r-vi-colab
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,11 +30,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# wav2vec2-large-xls-r-vi-colab
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Wer:
|
22 |
-
- Cer:
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,32 +53,28 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
-
- train_batch_size:
|
43 |
- eval_batch_size: 8
|
44 |
- seed: 42
|
|
|
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- lr_scheduler_warmup_steps:
|
48 |
- num_epochs: 30
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
54 |
-
|
55 |
-
|
|
56 |
-
| 3.
|
57 |
-
| 3.
|
58 |
-
| 3.
|
59 |
-
|
|
60 |
-
|
|
61 |
-
| 3.4112 | 16.7045 | 2205 | 4.5614 | 1.0 | 1.0 |
|
62 |
-
| 3.4074 | 19.0909 | 2520 | 4.3545 | 1.0 | 1.0 |
|
63 |
-
| 3.4073 | 21.4773 | 2835 | 4.4929 | 1.0 | 1.0 |
|
64 |
-
| 3.4004 | 23.8636 | 3150 | 4.6089 | 1.0 | 1.0 |
|
65 |
-
| 3.4099 | 26.25 | 3465 | 4.5189 | 1.0 | 1.0 |
|
66 |
-
| 3.3972 | 28.6364 | 3780 | 4.5540 | 1.0 | 1.0 |
|
67 |
|
68 |
|
69 |
### 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
|
19 |
+
config: vi
|
20 |
+
split: test[:50%]
|
21 |
+
args: vi
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.9155054191550542
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# wav2vec2-large-xls-r-vi-colab
|
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: 2.0995
|
36 |
+
- Wer: 0.9155
|
37 |
+
- Cer: 0.4345
|
38 |
|
39 |
## Model description
|
40 |
|
|
|
53 |
### Training hyperparameters
|
54 |
|
55 |
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 3e-05
|
57 |
+
- train_batch_size: 16
|
58 |
- eval_batch_size: 8
|
59 |
- seed: 42
|
60 |
+
- gradient_accumulation_steps: 2
|
61 |
+
- total_train_batch_size: 32
|
62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
- lr_scheduler_type: linear
|
64 |
+
- lr_scheduler_warmup_steps: 400
|
65 |
- num_epochs: 30
|
66 |
- mixed_precision_training: Native AMP
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
71 |
+
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:|
|
72 |
+
| 14.8797 | 4.4444 | 200 | 4.6129 | 1.0 | 1.0 |
|
73 |
+
| 3.9436 | 8.8889 | 400 | 3.5521 | 1.0 | 1.0 |
|
74 |
+
| 3.4845 | 13.3333 | 600 | 3.4997 | 1.0 | 1.0 |
|
75 |
+
| 3.1358 | 17.7778 | 800 | 2.7899 | 1.0011 | 0.7023 |
|
76 |
+
| 2.0727 | 22.2222 | 1000 | 2.2606 | 0.9600 | 0.4680 |
|
77 |
+
| 1.5218 | 26.6667 | 1200 | 2.0995 | 0.9155 | 0.4345 |
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
|
79 |
|
80 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377811068
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa45cd4b97890476b42e8c26b766ca76273cab6d8d650392301be034cb9f44ab
|
3 |
size 377811068
|
runs/Jul02_14-43-23_6883efef1353/events.out.tfevents.1719931446.6883efef1353.2517.0
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:c82096ec49a33a5aa4d544efc3b207920acca7564fe2a31709221e00c7abb761
|
3 |
+
size 10356
|