vioannidis
commited on
Commit
•
bfa28e5
1
Parent(s):
04fb240
update model card README.md
Browse files
README.md
CHANGED
@@ -5,9 +5,24 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice
|
|
|
|
|
8 |
model-index:
|
9 |
- name: wav2vec2-large-xls-r-300m-dutch-fast-colab
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -16,6 +31,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# wav2vec2-large-xls-r-300m-dutch-fast-colab
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,23 +53,26 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 0.0003
|
38 |
-
- train_batch_size:
|
39 |
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
- gradient_accumulation_steps: 2
|
42 |
-
- total_train_batch_size:
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 500
|
46 |
-
- num_epochs:
|
47 |
|
48 |
### Training results
|
49 |
|
|
|
|
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
53 |
|
54 |
- Transformers 4.31.0
|
55 |
- Pytorch 2.0.1+cu118
|
56 |
-
- Datasets 2.14.
|
57 |
- Tokenizers 0.13.3
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
model-index:
|
11 |
- name: wav2vec2-large-xls-r-300m-dutch-fast-colab
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Automatic Speech Recognition
|
15 |
+
type: automatic-speech-recognition
|
16 |
+
dataset:
|
17 |
+
name: common_voice
|
18 |
+
type: common_voice
|
19 |
+
config: nl
|
20 |
+
split: test
|
21 |
+
args: nl
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.9243053012734448
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
# wav2vec2-large-xls-r-300m-dutch-fast-colab
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.4526
|
36 |
+
- Wer: 0.9243
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 0.0003
|
56 |
+
- train_batch_size: 8
|
57 |
- eval_batch_size: 8
|
58 |
- seed: 42
|
59 |
- gradient_accumulation_steps: 2
|
60 |
+
- total_train_batch_size: 16
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 500
|
64 |
+
- num_epochs: 3
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
70 |
+
| 3.8222 | 1.65 | 400 | 1.4526 | 0.9243 |
|
71 |
|
72 |
|
73 |
### Framework versions
|
74 |
|
75 |
- Transformers 4.31.0
|
76 |
- Pytorch 2.0.1+cu118
|
77 |
+
- Datasets 2.14.4
|
78 |
- Tokenizers 0.13.3
|