Sandiago21
commited on
Commit
•
f59ccb3
1
Parent(s):
a59f63a
update model card README.md
Browse files
README.md
CHANGED
@@ -1,9 +1,11 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
-
- fleurs
|
7 |
metrics:
|
8 |
- wer
|
9 |
model-index:
|
@@ -13,15 +15,15 @@ model-index:
|
|
13 |
name: Automatic Speech Recognition
|
14 |
type: automatic-speech-recognition
|
15 |
dataset:
|
16 |
-
name:
|
17 |
-
type: fleurs
|
18 |
config: el_gr
|
19 |
split: test
|
20 |
args: el_gr
|
21 |
metrics:
|
22 |
- name: Wer
|
23 |
type: wer
|
24 |
-
value:
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,11 +31,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# whisper-large-v2-greek
|
31 |
|
32 |
-
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Wer Ortho:
|
36 |
-
- Wer:
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -61,22 +63,21 @@ The following hyperparameters were used during training:
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: constant_with_warmup
|
63 |
- lr_scheduler_warmup_steps: 50
|
64 |
-
- num_epochs:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.0039 | 9.97 | 2170 | 0.2061 | 1.0424 | 1.0565 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- el
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
+
- google/fleurs
|
9 |
metrics:
|
10 |
- wer
|
11 |
model-index:
|
|
|
15 |
name: Automatic Speech Recognition
|
16 |
type: automatic-speech-recognition
|
17 |
dataset:
|
18 |
+
name: FLEURS
|
19 |
+
type: google/fleurs
|
20 |
config: el_gr
|
21 |
split: test
|
22 |
args: el_gr
|
23 |
metrics:
|
24 |
- name: Wer
|
25 |
type: wer
|
26 |
+
value: 0.8398897182435613
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
# whisper-large-v2-greek
|
33 |
|
34 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the FLEURS dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.2442
|
37 |
+
- Wer Ortho: 0.8376
|
38 |
+
- Wer: 0.8399
|
39 |
|
40 |
## Model description
|
41 |
|
|
|
63 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
64 |
- lr_scheduler_type: constant_with_warmup
|
65 |
- lr_scheduler_warmup_steps: 50
|
66 |
+
- num_epochs: 9
|
67 |
|
68 |
### Training results
|
69 |
|
70 |
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|
71 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
|
72 |
+
| 0.1502 | 1.0 | 217 | 0.1780 | 1.1731 | 1.1960 |
|
73 |
+
| 0.0608 | 2.0 | 435 | 0.1869 | 1.1069 | 1.1209 |
|
74 |
+
| 0.0305 | 3.0 | 653 | 0.2029 | 1.1970 | 1.2144 |
|
75 |
+
| 0.0178 | 4.0 | 871 | 0.2186 | 1.3240 | 1.3458 |
|
76 |
+
| 0.0108 | 5.0 | 1088 | 0.2253 | 1.1080 | 1.1200 |
|
77 |
+
| 0.0076 | 6.0 | 1306 | 0.2301 | 1.0047 | 1.0155 |
|
78 |
+
| 0.0072 | 7.0 | 1524 | 0.2402 | 1.1153 | 1.1405 |
|
79 |
+
| 0.0051 | 8.0 | 1742 | 0.2434 | 1.0095 | 1.0264 |
|
80 |
+
| 0.0056 | 8.97 | 1953 | 0.2442 | 0.8376 | 0.8399 |
|
|
|
81 |
|
82 |
|
83 |
### Framework versions
|