Update generation_config.json
Browse filesCorrect alignment heads after analyzing the cross-attention weights using DTW averaging 20 samples from "librispeech". Tests showed better timestamp aligments than "whisper-small.en" especially in shorter samples (8-10 seconds).
- generation_config.json +1 -78
generation_config.json
CHANGED
|
@@ -1,82 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"alignment_heads": [
|
| 3 |
-
[
|
| 4 |
-
6,
|
| 5 |
-
6
|
| 6 |
-
],
|
| 7 |
-
[
|
| 8 |
-
7,
|
| 9 |
-
0
|
| 10 |
-
],
|
| 11 |
-
[
|
| 12 |
-
7,
|
| 13 |
-
3
|
| 14 |
-
],
|
| 15 |
-
[
|
| 16 |
-
7,
|
| 17 |
-
8
|
| 18 |
-
],
|
| 19 |
-
[
|
| 20 |
-
8,
|
| 21 |
-
2
|
| 22 |
-
],
|
| 23 |
-
[
|
| 24 |
-
8,
|
| 25 |
-
5
|
| 26 |
-
],
|
| 27 |
-
[
|
| 28 |
-
8,
|
| 29 |
-
7
|
| 30 |
-
],
|
| 31 |
-
[
|
| 32 |
-
9,
|
| 33 |
-
0
|
| 34 |
-
],
|
| 35 |
-
[
|
| 36 |
-
9,
|
| 37 |
-
4
|
| 38 |
-
],
|
| 39 |
-
[
|
| 40 |
-
9,
|
| 41 |
-
8
|
| 42 |
-
],
|
| 43 |
-
[
|
| 44 |
-
9,
|
| 45 |
-
10
|
| 46 |
-
],
|
| 47 |
-
[
|
| 48 |
-
10,
|
| 49 |
-
0
|
| 50 |
-
],
|
| 51 |
-
[
|
| 52 |
-
10,
|
| 53 |
-
1
|
| 54 |
-
],
|
| 55 |
-
[
|
| 56 |
-
10,
|
| 57 |
-
2
|
| 58 |
-
],
|
| 59 |
-
[
|
| 60 |
-
10,
|
| 61 |
-
3
|
| 62 |
-
],
|
| 63 |
-
[
|
| 64 |
-
10,
|
| 65 |
-
6
|
| 66 |
-
],
|
| 67 |
-
[
|
| 68 |
-
10,
|
| 69 |
-
11
|
| 70 |
-
],
|
| 71 |
-
[
|
| 72 |
-
11,
|
| 73 |
-
2
|
| 74 |
-
],
|
| 75 |
-
[
|
| 76 |
-
11,
|
| 77 |
-
4
|
| 78 |
-
]
|
| 79 |
-
],
|
| 80 |
"begin_suppress_tokens": [
|
| 81 |
220,
|
| 82 |
50256
|
|
|
|
| 1 |
{
|
| 2 |
+
"alignment_heads": [[1, 7], [2, 0], [2, 3], [2, 4], [3, 2], [3, 4], [3, 5], [3, 10]],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"begin_suppress_tokens": [
|
| 4 |
220,
|
| 5 |
50256
|