weekcircle
commited on
Commit
•
5e8e372
1
Parent(s):
f81864e
update model card README.md
Browse files
README.md
CHANGED
@@ -5,9 +5,24 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice_13_0
|
|
|
|
|
8 |
model-index:
|
9 |
- name: wav2vec2-large-mms-1b-korean-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-mms-1b-korean-colab
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/mms-1b-l1107](https://huggingface.co/facebook/mms-1b-l1107) on the common_voice_13_0 dataset.
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -41,10 +59,13 @@ The following hyperparameters were used during training:
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 100
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
|
|
|
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- common_voice_13_0
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
model-index:
|
11 |
- name: wav2vec2-large-mms-1b-korean-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: ko
|
20 |
+
split: test
|
21 |
+
args: ko
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 0.9969788519637462
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
# wav2vec2-large-mms-1b-korean-colab
|
32 |
|
33 |
This model is a fine-tuned version of [facebook/mms-1b-l1107](https://huggingface.co/facebook/mms-1b-l1107) on the common_voice_13_0 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 6.6168
|
36 |
+
- Wer: 0.9970
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
- lr_scheduler_warmup_steps: 100
|
62 |
+
- num_epochs: 8
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
68 |
+
| 5.7376 | 5.26 | 100 | 6.6168 | 0.9970 |
|
69 |
|
70 |
|
71 |
### Framework versions
|