Upload WhisperForConditionalGeneration
#4
by
linl03
- opened
- README.md +8 -8
- config.json +1 -1
- generation_config.json +27 -25
- model.safetensors +1 -1
README.md
CHANGED
@@ -1,20 +1,20 @@
|
|
1 |
---
|
2 |
-
library_name: transformers
|
3 |
-
language:
|
4 |
-
- vi
|
5 |
base_model: openai/whisper-small-v3
|
6 |
-
tags:
|
7 |
-
- generated_from_trainer
|
8 |
datasets:
|
9 |
- mozilla-foundation/common_voice_11_0
|
|
|
|
|
|
|
10 |
metrics:
|
11 |
- wer
|
|
|
|
|
12 |
model-index:
|
13 |
- name: Whisper small vi - Ox
|
14 |
results:
|
15 |
- task:
|
16 |
-
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
|
|
18 |
dataset:
|
19 |
name: Common Voice 11.0
|
20 |
type: mozilla-foundation/common_voice_11_0
|
@@ -22,9 +22,9 @@ model-index:
|
|
22 |
split: test
|
23 |
args: 'config: vi, split: test'
|
24 |
metrics:
|
25 |
-
-
|
26 |
-
type: wer
|
27 |
value: 14.738458164272398
|
|
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
1 |
---
|
|
|
|
|
|
|
2 |
base_model: openai/whisper-small-v3
|
|
|
|
|
3 |
datasets:
|
4 |
- mozilla-foundation/common_voice_11_0
|
5 |
+
language:
|
6 |
+
- vi
|
7 |
+
library_name: transformers
|
8 |
metrics:
|
9 |
- wer
|
10 |
+
tags:
|
11 |
+
- generated_from_trainer
|
12 |
model-index:
|
13 |
- name: Whisper small vi - Ox
|
14 |
results:
|
15 |
- task:
|
|
|
16 |
type: automatic-speech-recognition
|
17 |
+
name: Automatic Speech Recognition
|
18 |
dataset:
|
19 |
name: Common Voice 11.0
|
20 |
type: mozilla-foundation/common_voice_11_0
|
|
|
22 |
split: test
|
23 |
args: 'config: vi, split: test'
|
24 |
metrics:
|
25 |
+
- type: wer
|
|
|
26 |
value: 14.738458164272398
|
27 |
+
name: Wer
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "linl03/whisper-
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "linl03/whisper-small-vi",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
generation_config.json
CHANGED
@@ -1,44 +1,36 @@
|
|
1 |
{
|
2 |
"alignment_heads": [
|
3 |
[
|
4 |
-
|
5 |
-
|
6 |
-
],
|
7 |
-
[
|
8 |
-
5,
|
9 |
-
9
|
10 |
],
|
11 |
[
|
12 |
-
|
13 |
-
|
14 |
],
|
15 |
[
|
16 |
-
|
17 |
-
|
18 |
],
|
19 |
[
|
20 |
-
|
21 |
7
|
22 |
],
|
23 |
[
|
24 |
-
|
25 |
-
|
26 |
-
],
|
27 |
-
[
|
28 |
-
9,
|
29 |
-
0
|
30 |
],
|
31 |
[
|
32 |
-
|
33 |
-
|
34 |
],
|
35 |
[
|
36 |
-
|
37 |
-
|
38 |
],
|
39 |
[
|
40 |
-
|
41 |
-
|
42 |
]
|
43 |
],
|
44 |
"begin_suppress_tokens": [
|
@@ -48,6 +40,16 @@
|
|
48 |
"bos_token_id": 50257,
|
49 |
"decoder_start_token_id": 50258,
|
50 |
"eos_token_id": 50257,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
"is_multilingual": true,
|
52 |
"lang_to_id": {
|
53 |
"<|af|>": 50327,
|
@@ -150,7 +152,6 @@
|
|
150 |
"<|yo|>": 50325,
|
151 |
"<|zh|>": 50260
|
152 |
},
|
153 |
-
"language": "vi",
|
154 |
"max_initial_timestamp_index": 50,
|
155 |
"max_length": 448,
|
156 |
"no_timestamps_token_id": 50363,
|
@@ -241,11 +242,12 @@
|
|
241 |
49870,
|
242 |
50254,
|
243 |
50258,
|
|
|
|
|
244 |
50360,
|
245 |
50361,
|
246 |
50362
|
247 |
],
|
248 |
-
"task": "transcribe",
|
249 |
"task_to_id": {
|
250 |
"transcribe": 50359,
|
251 |
"translate": 50358
|
|
|
1 |
{
|
2 |
"alignment_heads": [
|
3 |
[
|
4 |
+
3,
|
5 |
+
1
|
|
|
|
|
|
|
|
|
6 |
],
|
7 |
[
|
8 |
+
4,
|
9 |
+
2
|
10 |
],
|
11 |
[
|
12 |
+
4,
|
13 |
+
3
|
14 |
],
|
15 |
[
|
16 |
+
4,
|
17 |
7
|
18 |
],
|
19 |
[
|
20 |
+
5,
|
21 |
+
1
|
|
|
|
|
|
|
|
|
22 |
],
|
23 |
[
|
24 |
+
5,
|
25 |
+
2
|
26 |
],
|
27 |
[
|
28 |
+
5,
|
29 |
+
4
|
30 |
],
|
31 |
[
|
32 |
+
5,
|
33 |
+
6
|
34 |
]
|
35 |
],
|
36 |
"begin_suppress_tokens": [
|
|
|
40 |
"bos_token_id": 50257,
|
41 |
"decoder_start_token_id": 50258,
|
42 |
"eos_token_id": 50257,
|
43 |
+
"forced_decoder_ids": [
|
44 |
+
[
|
45 |
+
1,
|
46 |
+
null
|
47 |
+
],
|
48 |
+
[
|
49 |
+
2,
|
50 |
+
50359
|
51 |
+
]
|
52 |
+
],
|
53 |
"is_multilingual": true,
|
54 |
"lang_to_id": {
|
55 |
"<|af|>": 50327,
|
|
|
152 |
"<|yo|>": 50325,
|
153 |
"<|zh|>": 50260
|
154 |
},
|
|
|
155 |
"max_initial_timestamp_index": 50,
|
156 |
"max_length": 448,
|
157 |
"no_timestamps_token_id": 50363,
|
|
|
242 |
49870,
|
243 |
50254,
|
244 |
50258,
|
245 |
+
50358,
|
246 |
+
50359,
|
247 |
50360,
|
248 |
50361,
|
249 |
50362
|
250 |
],
|
|
|
251 |
"task_to_id": {
|
252 |
"transcribe": 50359,
|
253 |
"translate": 50358
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 966995080
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e3c9a1451c4a1abb56ff3e11b3e6b7b8f444e189e161f21950a1a104cd724a1
|
3 |
size 966995080
|