Luigi commited on
Commit
dfa700d
·
verified ·
1 Parent(s): ab0f1bd

one-click rebuild_voice.sh + generators + text pools

Browse files
Files changed (1) hide show
  1. scripts/gen_codemix_v2.py +101 -0
scripts/gen_codemix_v2.py ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ """v2 code-mix generator — EXPANDED frame bank (more syntactic variety + English in more positions)
3
+ to push mix-CER below the 0.178 the v1 (40-frame) generator reached. Adds questions, longer multi-clause
4
+ frames, leading-English frames, and number/date-heavy frames. Dedups against an existing corpus.
5
+
6
+ Usage: python gen_codemix_v2.py --n 3000 --exclude codemix_corpus.txt --out codemix_v2.txt
7
+ """
8
+ import argparse, random, re
9
+
10
+ NAMES = ["Jason","Kelly","Daniel","Rita","Amy","Kevin","Linda","Peter","Vivian","Frank","Tom","Cindy",
11
+ "Eric","Grace","Sam","Joyce","Leo","Nina","Oscar","Sandy","Ryan","Emma","Jack","Mia","Henry",
12
+ "Chloe","Ivan","Wendy","Alan","Tina","Bella","George","Karen","Lucas","Sophie","Victor"]
13
+ SUR=["王","陳","林","李","張","黃","吳","劉","蔡","楊","許","鄭","謝","郭","洪","曾","廖","賴","周","葉"]
14
+ TITLE=["經理","助理","工程師","專員","主任","課長","副理","顧問","店長","總監","組長"]
15
+ DEPT=["技術部","客服部","業務部","品保部","財務部","人資部","採購部","研發部","行銷部","資訊部","法務部","物流部"]
16
+ APP=["App","Line","Email","Portal","Outlook","Teams","Slack","ERP 系統","CRM 系統","官網","Dropbox","Notion"]
17
+ ITEM=["Excel 報表","PDF 檔","QR Code","VIP 等級","Zoom 連結","email","發票","合約","報告書","專案","預算表",
18
+ "行事曆","購物車","訂單","帳號","密碼","會員卡","序號","授權碼","點數","報價單","出貨單","履歷","簡報"]
19
+ ACT=["login","logout","update","reset","upload","download","check","confirm","submit","cancel","review",
20
+ "approve","sync","backup","scan","forward","schedule","reschedule","verify","activate"]
21
+ STATUS=["ready","done","updated","confirmed","cancelled","pending","online","offline","expired","approved","rejected"]
22
+ EVENT=["meeting","Zoom 會議","conference call","interview","presentation","demo","workshop","training","kick-off"]
23
+ ADJ=["busy","urgent","important","ready","OK","fine","available","tied up"]
24
+ def ext(): return str(random.randint(1000,9999))
25
+ def num(): return str(random.randint(100000,999999))
26
+ def time_(): return random.choice(["上午九點","上午十點半","中午十二點","下午兩點","下午三點半","下午四點",
27
+ "明天上午","後天下午","這個禮拜五","下週一早上","月底前","這個月十五號","禮拜三中午"])
28
+ def disc(): return random.choice(["九折","八五折","七九折","買一送一","免運","現折五百"])
29
+
30
+ # v1's 40 frames are kept implicitly by overlap; here are NEW + varied ones (leading-English, questions,
31
+ # multi-clause, numeric). The fill() randomization over big slot lists yields tens of thousands distinct.
32
+ FRAMES = [
33
+ # leading / English-first
34
+ "Hi {name},您的{item}我已經 {act} 好了,要不要 double check 一下?",
35
+ "OK,那我先把這個 {event} {act} 到{time},confirm 後再通知您。",
36
+ "Sorry,{app} 剛剛 {status},您的{item}可能要重新 {act} 一次。",
37
+ "No problem,我請 {name} {sur}{title}在{time}前 {act} 完這份{item}。",
38
+ "Actually 這個 {item} 的 deadline 是{time},麻煩您 prioritize 一下。",
39
+ # questions
40
+ "請問您的 {app} 帳號是用 email 還是 phone number 註冊的?",
41
+ "您要的{item}是 standard 還是 premium 版,方便 confirm 一下嗎?",
42
+ "請問這個 {event} 的 link 您有收到嗎?還是要我 re-send?",
43
+ "{name} 的分機是 {ext} 對嗎?我幫您 transfer 過去好嗎?",
44
+ "您的{item}編號是不是 {num}?我這邊 check 一下 status。",
45
+ "請問{time}的 {event} 改到三樓還是線上 Zoom?",
46
+ # multi-clause
47
+ "您的訂單 {num} 已經 {status},預計{time}送達,tracking number 我用 Line 傳給您。",
48
+ "我先幫您把{item} {act},等 {dept} approve 之後,系統會自動 send 一封 email。",
49
+ "{name} {sur}{title}今天比較 {adj},不過他說{time}可以跟您 quick call 一下。",
50
+ "這個 case 我已經 {act} 到 CRM 系統,reference number 是 {num},有問題再撥分機 {ext}。",
51
+ "麻煩您先 {act} 一下{item},然後把 screenshot upload 到 {app},我這邊同步處理。",
52
+ "您的會員 {status},如果現在 upgrade 到 VIP,這個月可以多享{disc}的優惠。",
53
+ # numeric / scheduling heavy
54
+ "您預約的 {event} 是{time},地點在三樓,記得帶 ID card 上來 check in。",
55
+ "這批貨的 PO number 是 {num},預計{time}到,到了我會 update 給{dept}。",
56
+ "您的 password 已經 expired,請在{time}前用 {app} reset,不然帳號會被 lock。",
57
+ "退款 {num} 元已經 {status},三到五個 working day 會退回原本的 credit card。",
58
+ "{name} 的 {event} 我 reschedule 到{time}了,calendar invite 已經 send 給所有人。",
59
+ # service register
60
+ "您好,這裡是 {dept} customer service,請問需要什麼 help?",
61
+ "不好意思讓您 hold 這麼久,您的{item}我現在馬上幫您 {act}。",
62
+ "我幫您 note 在系統了,{name} 一上線就會 call back,大概{time}。",
63
+ "您的 {item} 目前 {status},如需 support 請撥分機 {ext} 找 {name}。",
64
+ "這份{item}我 convert 成 PDF 用 email 寄給您,subject 會註明{time}。",
65
+ "麻煩您 confirm 一下{time}方不方便,我再幫您把 {event} lock 起來。",
66
+ "您的 {app} 點數還有 {num} 點,結帳時可以 redeem 折抵{disc}。",
67
+ "好的 {name},我這邊 follow up 您的{item},有 update 第一時間 ping 您。",
68
+ ]
69
+
70
+ def fill(frame):
71
+ return frame.format(name=random.choice(NAMES),sur=random.choice(SUR),title=random.choice(TITLE),
72
+ dept=random.choice(DEPT),app=random.choice(APP),item=random.choice(ITEM),act=random.choice(ACT),
73
+ status=random.choice(STATUS),event=random.choice(EVENT),adj=random.choice(ADJ),
74
+ ext=ext(),num=num(),time=time_(),disc=disc())
75
+
76
+ def main():
77
+ ap=argparse.ArgumentParser()
78
+ ap.add_argument("--n",type=int,default=3000)
79
+ ap.add_argument("--exclude",default="codemix_corpus.txt")
80
+ ap.add_argument("--out",default="codemix_v2.txt")
81
+ ap.add_argument("--seed",type=int,default=7)
82
+ a=ap.parse_args()
83
+ random.seed(a.seed)
84
+ excl=set()
85
+ try: excl={l.strip() for l in open(a.exclude) if l.strip()}
86
+ except FileNotFoundError: pass
87
+ out,tries=set(),0
88
+ while len(out)<a.n and tries<a.n*60:
89
+ tries+=1
90
+ s=fill(random.choice(FRAMES))
91
+ if (re.search(r"[一-鿿]",s) and re.search(r"[A-Za-z]",s) and 10<=len(s)<=64
92
+ and s not in excl and s not in out):
93
+ out.add(s)
94
+ out=sorted(out)
95
+ open(a.out,"w",encoding="utf-8").write("\n".join(out)+"\n")
96
+ print(f"wrote {len(out)} NEW diverse code-mix sentences -> {a.out} ({len(FRAMES)} new frames, excl {len(excl)})")
97
+ import random as _r; _r.seed(1)
98
+ for s in _r.sample(out,8): print(" ",s)
99
+
100
+ if __name__=="__main__":
101
+ main()