Commit ·
5c7ee62
1
Parent(s): 7f78f97
copy files
Browse files- .gitattributes +15 -11
- am.mvn +8 -0
- chn_jpn_yue_eng_ko_spectok.bpe.model +3 -0
- config.yaml +97 -0
- configuration.json +14 -0
- example/.DS_Store +0 -0
- example/en.mp3 +0 -0
- example/ja.mp3 +0 -0
- example/ko.mp3 +0 -0
- example/yue.mp3 +0 -0
- example/zh.mp3 +0 -0
- fig/aed_figure.png +3 -0
- fig/asr_results.png +3 -0
- fig/inference.png +3 -0
- fig/sensevoice.png +3 -0
- fig/ser_figure.png +3 -0
- fig/ser_table.png +3 -0
- model.pt +3 -0
- tokens.json +0 -0
.gitattributes
CHANGED
|
@@ -1,35 +1,39 @@
|
|
| 1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 4 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
-
*.
|
| 35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
| 5 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 11 |
*.model filter=lfs diff=lfs merge=lfs -text
|
| 12 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
| 13 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 14 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 15 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 16 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
| 17 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 18 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 19 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 20 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 21 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 22 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 23 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 24 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.db* filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.ark* filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.ggml filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
*.wav filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
*.png filter=lfs diff=lfs merge=lfs -text
|
am.mvn
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<Nnet>
|
| 2 |
+
<Splice> 560 560
|
| 3 |
+
[ 0 ]
|
| 4 |
+
<AddShift> 560 560
|
| 5 |
+
<LearnRateCoef> 0 [ -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 -8.311879 -8.600912 -9.615928 -10.43595 -11.21292 -11.88333 -12.36243 -12.63706 -12.8818 -12.83066 -12.89103 -12.95666 -13.19763 -13.40598 -13.49113 -13.5546 -13.55639 -13.51915 -13.68284 -13.53289 -13.42107 -13.65519 -13.50713 -13.75251 -13.76715 -13.87408 -13.73109 -13.70412 -13.56073 -13.53488 -13.54895 -13.56228 -13.59408 -13.62047 -13.64198 -13.66109 -13.62669 -13.58297 -13.57387 -13.4739 -13.53063 -13.48348 -13.61047 -13.64716 -13.71546 -13.79184 -13.90614 -14.03098 -14.18205 -14.35881 -14.48419 -14.60172 -14.70591 -14.83362 -14.92122 -15.00622 -15.05122 -15.03119 -14.99028 -14.92302 -14.86927 -14.82691 -14.7972 -14.76909 -14.71356 -14.61277 -14.51696 -14.42252 -14.36405 -14.30451 -14.23161 -14.19851 -14.16633 -14.15649 -14.10504 -13.99518 -13.79562 -13.3996 -12.7767 -11.71208 ]
|
| 6 |
+
<Rescale> 560 560
|
| 7 |
+
<LearnRateCoef> 0 [ 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 0.155775 0.154484 0.1527379 0.1518718 0.1506028 0.1489256 0.147067 0.1447061 0.1436307 0.1443568 0.1451849 0.1455157 0.1452821 0.1445717 0.1439195 0.1435867 0.1436018 0.1438781 0.1442086 0.1448844 0.1454756 0.145663 0.146268 0.1467386 0.1472724 0.147664 0.1480913 0.1483739 0.1488841 0.1493636 0.1497088 0.1500379 0.1502916 0.1505389 0.1506787 0.1507102 0.1505992 0.1505445 0.1505938 0.1508133 0.1509569 0.1512396 0.1514625 0.1516195 0.1516156 0.1515561 0.1514966 0.1513976 0.1512612 0.151076 0.1510596 0.1510431 0.151077 0.1511168 0.1511917 0.151023 0.1508045 0.1505885 0.1503493 0.1502373 0.1501726 0.1500762 0.1500065 0.1499782 0.150057 0.1502658 0.150469 0.1505335 0.1505505 0.1505328 0.1504275 0.1502438 0.1499674 0.1497118 0.1494661 0.1493102 0.1493681 0.1495501 0.1499738 0.1509654 ]
|
| 8 |
+
</Nnet>
|
chn_jpn_yue_eng_ko_spectok.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa87f86064c3730d799ddf7af3c04659151102cba548bce325cf06ba4da4e6a8
|
| 3 |
+
size 377341
|
config.yaml
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
encoder: SenseVoiceEncoderSmall
|
| 2 |
+
encoder_conf:
|
| 3 |
+
output_size: 512
|
| 4 |
+
attention_heads: 4
|
| 5 |
+
linear_units: 2048
|
| 6 |
+
num_blocks: 50
|
| 7 |
+
tp_blocks: 20
|
| 8 |
+
dropout_rate: 0.1
|
| 9 |
+
positional_dropout_rate: 0.1
|
| 10 |
+
attention_dropout_rate: 0.1
|
| 11 |
+
input_layer: pe
|
| 12 |
+
pos_enc_class: SinusoidalPositionEncoder
|
| 13 |
+
normalize_before: true
|
| 14 |
+
kernel_size: 11
|
| 15 |
+
sanm_shfit: 0
|
| 16 |
+
selfattention_layer_type: sanm
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
model: SenseVoiceSmall
|
| 20 |
+
model_conf:
|
| 21 |
+
length_normalized_loss: true
|
| 22 |
+
sos: 1
|
| 23 |
+
eos: 2
|
| 24 |
+
ignore_id: -1
|
| 25 |
+
|
| 26 |
+
tokenizer: SentencepiecesTokenizer
|
| 27 |
+
tokenizer_conf:
|
| 28 |
+
bpemodel: null
|
| 29 |
+
unk_symbol: <unk>
|
| 30 |
+
split_with_space: true
|
| 31 |
+
|
| 32 |
+
frontend: WavFrontend
|
| 33 |
+
frontend_conf:
|
| 34 |
+
fs: 16000
|
| 35 |
+
window: hamming
|
| 36 |
+
n_mels: 80
|
| 37 |
+
frame_length: 25
|
| 38 |
+
frame_shift: 10
|
| 39 |
+
lfr_m: 7
|
| 40 |
+
lfr_n: 6
|
| 41 |
+
cmvn_file: null
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
dataset: SenseVoiceCTCDataset
|
| 45 |
+
dataset_conf:
|
| 46 |
+
index_ds: IndexDSJsonl
|
| 47 |
+
batch_sampler: EspnetStyleBatchSampler
|
| 48 |
+
data_split_num: 32
|
| 49 |
+
batch_type: token
|
| 50 |
+
batch_size: 14000
|
| 51 |
+
max_token_length: 2000
|
| 52 |
+
min_token_length: 60
|
| 53 |
+
max_source_length: 2000
|
| 54 |
+
min_source_length: 60
|
| 55 |
+
max_target_length: 200
|
| 56 |
+
min_target_length: 0
|
| 57 |
+
shuffle: true
|
| 58 |
+
num_workers: 4
|
| 59 |
+
sos: ${model_conf.sos}
|
| 60 |
+
eos: ${model_conf.eos}
|
| 61 |
+
IndexDSJsonl: IndexDSJsonl
|
| 62 |
+
retry: 20
|
| 63 |
+
|
| 64 |
+
train_conf:
|
| 65 |
+
accum_grad: 1
|
| 66 |
+
grad_clip: 5
|
| 67 |
+
max_epoch: 20
|
| 68 |
+
keep_nbest_models: 10
|
| 69 |
+
avg_nbest_model: 10
|
| 70 |
+
log_interval: 100
|
| 71 |
+
resume: true
|
| 72 |
+
validate_interval: 10000
|
| 73 |
+
save_checkpoint_interval: 10000
|
| 74 |
+
|
| 75 |
+
optim: adamw
|
| 76 |
+
optim_conf:
|
| 77 |
+
lr: 0.00002
|
| 78 |
+
scheduler: warmuplr
|
| 79 |
+
scheduler_conf:
|
| 80 |
+
warmup_steps: 25000
|
| 81 |
+
|
| 82 |
+
specaug: SpecAugLFR
|
| 83 |
+
specaug_conf:
|
| 84 |
+
apply_time_warp: false
|
| 85 |
+
time_warp_window: 5
|
| 86 |
+
time_warp_mode: bicubic
|
| 87 |
+
apply_freq_mask: true
|
| 88 |
+
freq_mask_width_range:
|
| 89 |
+
- 0
|
| 90 |
+
- 30
|
| 91 |
+
lfr_rate: 6
|
| 92 |
+
num_freq_mask: 1
|
| 93 |
+
apply_time_mask: true
|
| 94 |
+
time_mask_width_range:
|
| 95 |
+
- 0
|
| 96 |
+
- 12
|
| 97 |
+
num_time_mask: 1
|
configuration.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"framework": "pytorch",
|
| 3 |
+
"task" : "auto-speech-recognition",
|
| 4 |
+
"model": {"type" : "funasr"},
|
| 5 |
+
"pipeline": {"type":"funasr-pipeline"},
|
| 6 |
+
"model_name_in_hub": {
|
| 7 |
+
"ms":"",
|
| 8 |
+
"hf":""},
|
| 9 |
+
"file_path_metas": {
|
| 10 |
+
"init_param":"model.pt",
|
| 11 |
+
"config":"config.yaml",
|
| 12 |
+
"tokenizer_conf": {"bpemodel": "chn_jpn_yue_eng_ko_spectok.bpe.model"},
|
| 13 |
+
"frontend_conf":{"cmvn_file": "am.mvn"}}
|
| 14 |
+
}
|
example/.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
example/en.mp3
ADDED
|
Binary file (57.4 kB). View file
|
|
|
example/ja.mp3
ADDED
|
Binary file (57.8 kB). View file
|
|
|
example/ko.mp3
ADDED
|
Binary file (27.9 kB). View file
|
|
|
example/yue.mp3
ADDED
|
Binary file (31.2 kB). View file
|
|
|
example/zh.mp3
ADDED
|
Binary file (45 kB). View file
|
|
|
fig/aed_figure.png
ADDED
|
Git LFS Details
|
fig/asr_results.png
ADDED
|
Git LFS Details
|
fig/inference.png
ADDED
|
Git LFS Details
|
fig/sensevoice.png
ADDED
|
Git LFS Details
|
fig/ser_figure.png
ADDED
|
Git LFS Details
|
fig/ser_table.png
ADDED
|
Git LFS Details
|
model.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:833ca2dcfdf8ec91bd4f31cfac36d6124e0c459074d5e909aec9cabe6204a3ea
|
| 3 |
+
size 936291369
|
tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|