Upload README materials
Browse files- .gitattributes +20 -0
- assets/dialogues/demo_dialogue1.wav +3 -0
- assets/dialogues/demo_dialogue2.wav +3 -0
- assets/dialogues/demo_dialogue3.wav +3 -0
- assets/img/model_architecture.png +3 -0
- assets/multi_turn.json +11 -0
- assets/ref/female1.wav +3 -0
- assets/ref/female2.wav +3 -0
- assets/ref/male1.wav +3 -0
- assets/ref/male2.wav +3 -0
- assets/single_turn.json +62 -0
- assets/synth/female1_sent1.wav +3 -0
- assets/synth/female1_sent2.wav +3 -0
- assets/synth/female1_sent3.wav +3 -0
- assets/synth/female2_sent4.wav +3 -0
- assets/synth/female2_sent5.wav +3 -0
- assets/synth/female2_sent6.wav +3 -0
- assets/synth/male1_sent7.wav +3 -0
- assets/synth/male1_sent8.wav +3 -0
- assets/synth/male1_sent9.wav +3 -0
- assets/synth/male2_sent10.wav +3 -0
- assets/synth/male2_sent11.wav +3 -0
- assets/synth/male2_sent12.wav +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,23 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
assets/dialogues/demo_dialogue1.wav filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
assets/dialogues/demo_dialogue2.wav filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
assets/dialogues/demo_dialogue3.wav filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
assets/img/model_architecture.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
assets/ref/female1.wav filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
assets/ref/female2.wav filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
assets/ref/male1.wav filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
assets/ref/male2.wav filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
assets/synth/female1_sent1.wav filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
assets/synth/female1_sent2.wav filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
assets/synth/female1_sent3.wav filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
assets/synth/female2_sent4.wav filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
assets/synth/female2_sent5.wav filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
assets/synth/female2_sent6.wav filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
assets/synth/male1_sent7.wav filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
assets/synth/male1_sent8.wav filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
assets/synth/male1_sent9.wav filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
assets/synth/male2_sent10.wav filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
assets/synth/male2_sent11.wav filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
assets/synth/male2_sent12.wav filter=lfs diff=lfs merge=lfs -text
|
assets/dialogues/demo_dialogue1.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1db83e290db0c16bf9c804b0e3b0e84d549697f05cc32fd73e904ba1d53cc27
|
| 3 |
+
size 15288916
|
assets/dialogues/demo_dialogue2.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7954c597f9cdd41c96775e336941005d92a6500bcd54d20bc30929632f5c0db6
|
| 3 |
+
size 7826822
|
assets/dialogues/demo_dialogue3.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6804ef632f38608f41b008e6922cafda5556b2f9da2e4a300dbd7359e93dad7b
|
| 3 |
+
size 9414866
|
assets/img/model_architecture.png
ADDED
|
Git LFS Details
|
assets/multi_turn.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"audio_path":"assets/dialogues/demo_dialogue1.wav"
|
| 4 |
+
},
|
| 5 |
+
{
|
| 6 |
+
"audio_path":"assets/dialogues/demo_dialogue2.wav"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"audio_path":"assets/dialogues/demo_dialogue3.wav"
|
| 10 |
+
}
|
| 11 |
+
]
|
assets/ref/female1.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c83b545d9dafd974d6970ae0c79a5ab43146e4dc0f337538165c201b83a97fa
|
| 3 |
+
size 172844
|
assets/ref/female2.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:817e4f7985099fb258de94117e2b95ea018cdafeeb9f887035ba5f3a9e8a31cc
|
| 3 |
+
size 213410
|
assets/ref/male1.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:740b156aea0c434e29022f55600fed5070f66962c38d1daabec31fcd9ca62f17
|
| 3 |
+
size 220844
|
assets/ref/male2.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44a7ee382f7fa7f3c626e767bb4f9d72c82a2119432a6429a1264f3c250a5395
|
| 3 |
+
size 353804
|
assets/single_turn.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"reference": "assets/ref/female1.wav",
|
| 4 |
+
"audio_path": "assets/synth/female1_sent1.wav",
|
| 5 |
+
"text": "那肯定因为自个儿平时想吃点卤味儿。那肯定得得得来一点儿。"
|
| 6 |
+
},
|
| 7 |
+
{
|
| 8 |
+
"reference": "assets/ref/female1.wav",
|
| 9 |
+
"audio_path": "assets/synth/female1_sent2.wav",
|
| 10 |
+
"text": "过年应该应该跟家里人一起吃饭。"
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"reference": "assets/ref/female1.wav",
|
| 14 |
+
"audio_path": "assets/synth/female1_sent3.wav",
|
| 15 |
+
"text": "哎呀,不是了,现在法治社会哪有卖假货的,只是卖的价格贵。"
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"reference": "assets/ref/female2.wav",
|
| 19 |
+
"audio_path": "assets/synth/female2_sent4.wav",
|
| 20 |
+
"text": "但是这个时候上哪去找呢?找不到。"
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"reference": "assets/ref/female2.wav",
|
| 24 |
+
"audio_path": "assets/synth/female2_sent5.wav",
|
| 25 |
+
"text": "这种做法我感觉不适合,不是他那个年龄段该做出来的事情。"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"reference": "assets/ref/female2.wav",
|
| 29 |
+
"audio_path": "assets/synth/female2_sent6.wav",
|
| 30 |
+
"text": "咱们得趁这个时机啊,看看还要剩多多久啊。"
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"reference": "assets/ref/male1.wav",
|
| 34 |
+
"audio_path": "assets/synth/male1_sent7.wav",
|
| 35 |
+
"text": "我我不不怎么玩游戏,你你会玩游戏啊。"
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"reference": "assets/ref/male1.wav",
|
| 39 |
+
"audio_path": "assets/synth/male1_sent8.wav",
|
| 40 |
+
"text": "对呀,就是不管你愿不愿意,时间都是一直往前推嘛。"
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"reference": "assets/ref/male1.wav",
|
| 44 |
+
"audio_path": "assets/synth/male1_sent9.wav",
|
| 45 |
+
"text": "挺好,我看着我看你做菜做饭蛮有生活的那是鸡蛋糕吗?"
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"reference": "assets/ref/male2.wav",
|
| 49 |
+
"audio_path": "assets/synth/male2_sent10.wav",
|
| 50 |
+
"text": "我也有二十多岁的时候,那个时候什么都不想,嗯,等那一点点沉淀,年龄大一点了,然后就什么都在乎,什么都想。"
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"reference": "assets/ref/male2.wav",
|
| 54 |
+
"audio_path": "assets/synth/male2_sent11.wav",
|
| 55 |
+
"text": "我看我一会儿,我我煮个泡面得了。"
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"reference": "assets/ref/male2.wav",
|
| 59 |
+
"audio_path": "assets/synth/male2_sent12.wav",
|
| 60 |
+
"text": "他们说那个茶茶饼就是渣子压出来的,是吗?"
|
| 61 |
+
}
|
| 62 |
+
]
|
assets/synth/female1_sent1.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a3155052d8fbd6417eb432a31bf525125c0a05a22bdb3809645afe62e264c75
|
| 3 |
+
size 282024
|
assets/synth/female1_sent2.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2eb714e50b1a26f73516d873a659a8a95a80b1b1536ee170184f2e3ad5284d19
|
| 3 |
+
size 178344
|
assets/synth/female1_sent3.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0024c0aa281090bd09db76d60a47d810405d1d3351f0f7ee19442045c2b6cab3
|
| 3 |
+
size 399144
|
assets/synth/female2_sent4.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d65659dd471fea1bbd09a2549879b0706f479f0e89278617482ab6c392cb8a1b
|
| 3 |
+
size 171624
|
assets/synth/female2_sent5.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbf9fea17ccdfdd9b81a288c4686575df90e5fcd50e28f03ff696c2cdaf85c59
|
| 3 |
+
size 280920
|
assets/synth/female2_sent6.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20b6fef0b84cf044965097584bf6e8c00d57561f29cee80c40973e27ec4bd4dd
|
| 3 |
+
size 228192
|
assets/synth/male1_sent7.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab8ade8faa9d2ca3b1be5700b5a75a9d1ea1e73dde4a3615941112815610c73a
|
| 3 |
+
size 181224
|
assets/synth/male1_sent8.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29dc8d91863a485c7dcc2cbc823cd0caa1987a067176d45a39db758897aadb91
|
| 3 |
+
size 242664
|
assets/synth/male1_sent9.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d04910e7fcc113499b0db87955ebc47c325dbcf62ff0b972ae7e6e861b94067c
|
| 3 |
+
size 300264
|
assets/synth/male2_sent10.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3a23894c3c2096b0d4de0b8d90659468fd869a0ade2ecb2dcc5d3a0e43b4538
|
| 3 |
+
size 552744
|
assets/synth/male2_sent11.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62d91752f21343f32b0b69bb5f58583ea92527e7f232fc9a7974f6bd83627ab1
|
| 3 |
+
size 207144
|
assets/synth/male2_sent12.wav
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0834ff47a89e6866bcf78eb603b3230113dc1292b9be7c1ad480d10ff7782d49
|
| 3 |
+
size 228264
|