minor updates
Browse files- .gitignore +2 -0
- err2020/conformer_ctc3_usage.ipynb +94 -30
.gitignore
CHANGED
|
@@ -1,2 +1,4 @@
|
|
| 1 |
**/.ipynb_checkpoints/
|
| 2 |
.idea/
|
|
|
|
|
|
|
|
|
| 1 |
**/.ipynb_checkpoints/
|
| 2 |
.idea/
|
| 3 |
+
__pycache__
|
| 4 |
+
**/__pycache__
|
err2020/conformer_ctc3_usage.ipynb
CHANGED
|
@@ -2,9 +2,13 @@
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
-
"execution_count":
|
| 6 |
"id": "b6b6ded1-0a58-43cb-9065-4f4fae02a01b",
|
| 7 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"outputs": [],
|
| 9 |
"source": [
|
| 10 |
"import argparse\n",
|
|
@@ -35,7 +39,11 @@
|
|
| 35 |
{
|
| 36 |
"cell_type": "markdown",
|
| 37 |
"id": "52514f2f-1195-4e4f-8174-d21aa7462476",
|
| 38 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
"source": [
|
| 40 |
"## Helpers"
|
| 41 |
]
|
|
@@ -43,16 +51,24 @@
|
|
| 43 |
{
|
| 44 |
"cell_type": "markdown",
|
| 45 |
"id": "8ec024bf-7f91-47a9-9293-822fe2765c4b",
|
| 46 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
"source": [
|
| 48 |
"#### Load args helpers"
|
| 49 |
]
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"cell_type": "code",
|
| 53 |
-
"execution_count":
|
| 54 |
"id": "3d69d771-b421-417f-a6ff-e1d1c64ba934",
|
| 55 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
"outputs": [],
|
| 57 |
"source": [
|
| 58 |
"class Args:\n",
|
|
@@ -114,16 +130,24 @@
|
|
| 114 |
{
|
| 115 |
"cell_type": "markdown",
|
| 116 |
"id": "57a3cd62-3037-4c99-9094-dd63429e660e",
|
| 117 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
"source": [
|
| 119 |
"#### Decoder helper"
|
| 120 |
]
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"cell_type": "code",
|
| 124 |
-
"execution_count":
|
| 125 |
"id": "48306369-fb68-4abe-be62-0806d00059f8",
|
| 126 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
"outputs": [],
|
| 128 |
"source": [
|
| 129 |
"class ConformerCtc3Decoder:\n",
|
|
@@ -385,16 +409,24 @@
|
|
| 385 |
{
|
| 386 |
"cell_type": "markdown",
|
| 387 |
"id": "b1464957-05b6-40f8-a1aa-c58edbed440c",
|
| 388 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 389 |
"source": [
|
| 390 |
"## Example usage"
|
| 391 |
]
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"cell_type": "code",
|
| 395 |
-
"execution_count":
|
| 396 |
"id": "50ab7c8e-39b6-4783-8342-e79e91d2417e",
|
| 397 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 398 |
"outputs": [],
|
| 399 |
"source": [
|
| 400 |
"#create transcriber/decoder object\n",
|
|
@@ -406,16 +438,20 @@
|
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"cell_type": "code",
|
| 409 |
-
"execution_count":
|
| 410 |
"id": "8020f371-7584-4f6c-990b-f2c023e24060",
|
| 411 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 412 |
"outputs": [
|
| 413 |
{
|
| 414 |
"name": "stdout",
|
| 415 |
"output_type": "stream",
|
| 416 |
"text": [
|
| 417 |
-
"CPU times: user
|
| 418 |
-
"Wall time: 4.
|
| 419 |
]
|
| 420 |
},
|
| 421 |
{
|
|
@@ -437,7 +473,7 @@
|
|
| 437 |
" {'word': 'panna', 'start': 10.16, 'end': 10.4}]}"
|
| 438 |
]
|
| 439 |
},
|
| 440 |
-
"execution_count":
|
| 441 |
"metadata": {},
|
| 442 |
"output_type": "execute_result"
|
| 443 |
}
|
|
@@ -449,16 +485,20 @@
|
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"cell_type": "code",
|
| 452 |
-
"execution_count":
|
| 453 |
"id": "4d2a480d-f0aa-4474-bfdb-ad298a629ce5",
|
| 454 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 455 |
"outputs": [
|
| 456 |
{
|
| 457 |
"name": "stdout",
|
| 458 |
"output_type": "stream",
|
| 459 |
"text": [
|
| 460 |
-
"CPU times: user
|
| 461 |
-
"Wall time:
|
| 462 |
]
|
| 463 |
}
|
| 464 |
],
|
|
@@ -468,9 +508,13 @@
|
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"cell_type": "code",
|
| 471 |
-
"execution_count":
|
| 472 |
"id": "d3827548-bca0-4409-95bc-9aa8ba377135",
|
| 473 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 474 |
"outputs": [
|
| 475 |
{
|
| 476 |
"data": {
|
|
@@ -592,7 +636,7 @@
|
|
| 592 |
" {'word': 'jah', 'start': 47.56, 'end': 47.68}]}"
|
| 593 |
]
|
| 594 |
},
|
| 595 |
-
"execution_count":
|
| 596 |
"metadata": {},
|
| 597 |
"output_type": "execute_result"
|
| 598 |
}
|
|
@@ -604,7 +648,11 @@
|
|
| 604 |
{
|
| 605 |
"cell_type": "markdown",
|
| 606 |
"id": "6740a04c-09e1-4497-84e2-5227acd9dda3",
|
| 607 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 608 |
"source": [
|
| 609 |
"## Some other decoding"
|
| 610 |
]
|
|
@@ -612,7 +660,11 @@
|
|
| 612 |
{
|
| 613 |
"cell_type": "markdown",
|
| 614 |
"id": "b012c0d7-04ab-451e-8414-85b4b9ac9165",
|
| 615 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 616 |
"source": [
|
| 617 |
"1best decoding currently not working"
|
| 618 |
]
|
|
@@ -621,7 +673,11 @@
|
|
| 621 |
"cell_type": "code",
|
| 622 |
"execution_count": 27,
|
| 623 |
"id": "15fcf012-265a-4464-8da7-1c7e1a46556a",
|
| 624 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 625 |
"outputs": [
|
| 626 |
{
|
| 627 |
"name": "stdout",
|
|
@@ -662,7 +718,11 @@
|
|
| 662 |
"cell_type": "code",
|
| 663 |
"execution_count": 28,
|
| 664 |
"id": "31591ee0-605c-4b20-b01f-cb8643fefdd1",
|
| 665 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 666 |
"outputs": [
|
| 667 |
{
|
| 668 |
"name": "stdout",
|
|
@@ -704,7 +764,11 @@
|
|
| 704 |
"cell_type": "code",
|
| 705 |
"execution_count": null,
|
| 706 |
"id": "80dfe34d-a76b-4ddc-a47c-c481c5e1432f",
|
| 707 |
-
"metadata": {
|
|
|
|
|
|
|
|
|
|
|
|
|
| 708 |
"outputs": [],
|
| 709 |
"source": []
|
| 710 |
}
|
|
@@ -730,4 +794,4 @@
|
|
| 730 |
},
|
| 731 |
"nbformat": 4,
|
| 732 |
"nbformat_minor": 5
|
| 733 |
-
}
|
|
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
+
"execution_count": 4,
|
| 6 |
"id": "b6b6ded1-0a58-43cb-9065-4f4fae02a01b",
|
| 7 |
+
"metadata": {
|
| 8 |
+
"pycharm": {
|
| 9 |
+
"name": "#%%\n"
|
| 10 |
+
}
|
| 11 |
+
},
|
| 12 |
"outputs": [],
|
| 13 |
"source": [
|
| 14 |
"import argparse\n",
|
|
|
|
| 39 |
{
|
| 40 |
"cell_type": "markdown",
|
| 41 |
"id": "52514f2f-1195-4e4f-8174-d21aa7462476",
|
| 42 |
+
"metadata": {
|
| 43 |
+
"pycharm": {
|
| 44 |
+
"name": "#%% md\n"
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
"source": [
|
| 48 |
"## Helpers"
|
| 49 |
]
|
|
|
|
| 51 |
{
|
| 52 |
"cell_type": "markdown",
|
| 53 |
"id": "8ec024bf-7f91-47a9-9293-822fe2765c4b",
|
| 54 |
+
"metadata": {
|
| 55 |
+
"pycharm": {
|
| 56 |
+
"name": "#%% md\n"
|
| 57 |
+
}
|
| 58 |
+
},
|
| 59 |
"source": [
|
| 60 |
"#### Load args helpers"
|
| 61 |
]
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"cell_type": "code",
|
| 65 |
+
"execution_count": 5,
|
| 66 |
"id": "3d69d771-b421-417f-a6ff-e1d1c64ba934",
|
| 67 |
+
"metadata": {
|
| 68 |
+
"pycharm": {
|
| 69 |
+
"name": "#%%\n"
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
"outputs": [],
|
| 73 |
"source": [
|
| 74 |
"class Args:\n",
|
|
|
|
| 130 |
{
|
| 131 |
"cell_type": "markdown",
|
| 132 |
"id": "57a3cd62-3037-4c99-9094-dd63429e660e",
|
| 133 |
+
"metadata": {
|
| 134 |
+
"pycharm": {
|
| 135 |
+
"name": "#%% md\n"
|
| 136 |
+
}
|
| 137 |
+
},
|
| 138 |
"source": [
|
| 139 |
"#### Decoder helper"
|
| 140 |
]
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"cell_type": "code",
|
| 144 |
+
"execution_count": 6,
|
| 145 |
"id": "48306369-fb68-4abe-be62-0806d00059f8",
|
| 146 |
+
"metadata": {
|
| 147 |
+
"pycharm": {
|
| 148 |
+
"name": "#%%\n"
|
| 149 |
+
}
|
| 150 |
+
},
|
| 151 |
"outputs": [],
|
| 152 |
"source": [
|
| 153 |
"class ConformerCtc3Decoder:\n",
|
|
|
|
| 409 |
{
|
| 410 |
"cell_type": "markdown",
|
| 411 |
"id": "b1464957-05b6-40f8-a1aa-c58edbed440c",
|
| 412 |
+
"metadata": {
|
| 413 |
+
"pycharm": {
|
| 414 |
+
"name": "#%% md\n"
|
| 415 |
+
}
|
| 416 |
+
},
|
| 417 |
"source": [
|
| 418 |
"## Example usage"
|
| 419 |
]
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"cell_type": "code",
|
| 423 |
+
"execution_count": 7,
|
| 424 |
"id": "50ab7c8e-39b6-4783-8342-e79e91d2417e",
|
| 425 |
+
"metadata": {
|
| 426 |
+
"pycharm": {
|
| 427 |
+
"name": "#%%\n"
|
| 428 |
+
}
|
| 429 |
+
},
|
| 430 |
"outputs": [],
|
| 431 |
"source": [
|
| 432 |
"#create transcriber/decoder object\n",
|
|
|
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"cell_type": "code",
|
| 441 |
+
"execution_count": 8,
|
| 442 |
"id": "8020f371-7584-4f6c-990b-f2c023e24060",
|
| 443 |
+
"metadata": {
|
| 444 |
+
"pycharm": {
|
| 445 |
+
"name": "#%%\n"
|
| 446 |
+
}
|
| 447 |
+
},
|
| 448 |
"outputs": [
|
| 449 |
{
|
| 450 |
"name": "stdout",
|
| 451 |
"output_type": "stream",
|
| 452 |
"text": [
|
| 453 |
+
"CPU times: user 4.83 s, sys: 210 ms, total: 5.04 s\n",
|
| 454 |
+
"Wall time: 4.13 s\n"
|
| 455 |
]
|
| 456 |
},
|
| 457 |
{
|
|
|
|
| 473 |
" {'word': 'panna', 'start': 10.16, 'end': 10.4}]}"
|
| 474 |
]
|
| 475 |
},
|
| 476 |
+
"execution_count": 8,
|
| 477 |
"metadata": {},
|
| 478 |
"output_type": "execute_result"
|
| 479 |
}
|
|
|
|
| 485 |
},
|
| 486 |
{
|
| 487 |
"cell_type": "code",
|
| 488 |
+
"execution_count": 9,
|
| 489 |
"id": "4d2a480d-f0aa-4474-bfdb-ad298a629ce5",
|
| 490 |
+
"metadata": {
|
| 491 |
+
"pycharm": {
|
| 492 |
+
"name": "#%%\n"
|
| 493 |
+
}
|
| 494 |
+
},
|
| 495 |
"outputs": [
|
| 496 |
{
|
| 497 |
"name": "stdout",
|
| 498 |
"output_type": "stream",
|
| 499 |
"text": [
|
| 500 |
+
"CPU times: user 16 s, sys: 1.13 s, total: 17.2 s\n",
|
| 501 |
+
"Wall time: 14.4 s\n"
|
| 502 |
]
|
| 503 |
}
|
| 504 |
],
|
|
|
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"cell_type": "code",
|
| 511 |
+
"execution_count": 10,
|
| 512 |
"id": "d3827548-bca0-4409-95bc-9aa8ba377135",
|
| 513 |
+
"metadata": {
|
| 514 |
+
"pycharm": {
|
| 515 |
+
"name": "#%%\n"
|
| 516 |
+
}
|
| 517 |
+
},
|
| 518 |
"outputs": [
|
| 519 |
{
|
| 520 |
"data": {
|
|
|
|
| 636 |
" {'word': 'jah', 'start': 47.56, 'end': 47.68}]}"
|
| 637 |
]
|
| 638 |
},
|
| 639 |
+
"execution_count": 10,
|
| 640 |
"metadata": {},
|
| 641 |
"output_type": "execute_result"
|
| 642 |
}
|
|
|
|
| 648 |
{
|
| 649 |
"cell_type": "markdown",
|
| 650 |
"id": "6740a04c-09e1-4497-84e2-5227acd9dda3",
|
| 651 |
+
"metadata": {
|
| 652 |
+
"pycharm": {
|
| 653 |
+
"name": "#%% md\n"
|
| 654 |
+
}
|
| 655 |
+
},
|
| 656 |
"source": [
|
| 657 |
"## Some other decoding"
|
| 658 |
]
|
|
|
|
| 660 |
{
|
| 661 |
"cell_type": "markdown",
|
| 662 |
"id": "b012c0d7-04ab-451e-8414-85b4b9ac9165",
|
| 663 |
+
"metadata": {
|
| 664 |
+
"pycharm": {
|
| 665 |
+
"name": "#%% md\n"
|
| 666 |
+
}
|
| 667 |
+
},
|
| 668 |
"source": [
|
| 669 |
"1best decoding currently not working"
|
| 670 |
]
|
|
|
|
| 673 |
"cell_type": "code",
|
| 674 |
"execution_count": 27,
|
| 675 |
"id": "15fcf012-265a-4464-8da7-1c7e1a46556a",
|
| 676 |
+
"metadata": {
|
| 677 |
+
"pycharm": {
|
| 678 |
+
"name": "#%%\n"
|
| 679 |
+
}
|
| 680 |
+
},
|
| 681 |
"outputs": [
|
| 682 |
{
|
| 683 |
"name": "stdout",
|
|
|
|
| 718 |
"cell_type": "code",
|
| 719 |
"execution_count": 28,
|
| 720 |
"id": "31591ee0-605c-4b20-b01f-cb8643fefdd1",
|
| 721 |
+
"metadata": {
|
| 722 |
+
"pycharm": {
|
| 723 |
+
"name": "#%%\n"
|
| 724 |
+
}
|
| 725 |
+
},
|
| 726 |
"outputs": [
|
| 727 |
{
|
| 728 |
"name": "stdout",
|
|
|
|
| 764 |
"cell_type": "code",
|
| 765 |
"execution_count": null,
|
| 766 |
"id": "80dfe34d-a76b-4ddc-a47c-c481c5e1432f",
|
| 767 |
+
"metadata": {
|
| 768 |
+
"pycharm": {
|
| 769 |
+
"name": "#%%\n"
|
| 770 |
+
}
|
| 771 |
+
},
|
| 772 |
"outputs": [],
|
| 773 |
"source": []
|
| 774 |
}
|
|
|
|
| 794 |
},
|
| 795 |
"nbformat": 4,
|
| 796 |
"nbformat_minor": 5
|
| 797 |
+
}
|