Text-to-Speech
ONNX
GGUF
Chinese
English
onnxruntime
tts
on-device
jetson
telephony
vits
mb-istft-vits
multi-speaker
mandarin
taiwanese-mandarin
imatrix
conversational
Instructions to use Luigi/PrimeTTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Luigi/PrimeTTS with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Luigi/PrimeTTS:F32 # Run inference directly in the terminal: llama cli -hf Luigi/PrimeTTS:F32
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Luigi/PrimeTTS:F32 # Run inference directly in the terminal: llama cli -hf Luigi/PrimeTTS:F32
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Luigi/PrimeTTS:F32 # Run inference directly in the terminal: ./llama-cli -hf Luigi/PrimeTTS:F32
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Luigi/PrimeTTS:F32 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Luigi/PrimeTTS:F32
Use Docker
docker model run hf.co/Luigi/PrimeTTS:F32
- LM Studio
- Jan
- Ollama
How to use Luigi/PrimeTTS with Ollama:
ollama run hf.co/Luigi/PrimeTTS:F32
- Unsloth Studio
How to use Luigi/PrimeTTS with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Luigi/PrimeTTS to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Luigi/PrimeTTS to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Luigi/PrimeTTS to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Luigi/PrimeTTS with Docker Model Runner:
docker model run hf.co/Luigi/PrimeTTS:F32
- Lemonade
How to use Luigi/PrimeTTS with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Luigi/PrimeTTS:F32
Run and chat with the model
lemonade run user.PrimeTTS-F32
List all available models
lemonade list
| #!/usr/bin/env python3 | |
| """Generate DIVERSE zh-TW + English code-mix sentences to fix the mix-CER weak spot. | |
| The existing corpus code-mix (~4.4k rows) is templated — a few frames repeated with swapped English | |
| nouns — so the model overfits frames and fails on diverse eval code-mix (mix CER 0.318). This builds a | |
| broad frame bank (varied syntax + English in varied positions) x varied insertions -> many distinct | |
| sentences, matching the Taiwan office / phone-attendant register the eval set uses. | |
| Usage: python gen_codemix.py --n 2800 --out codemix_corpus.txt | |
| """ | |
| import argparse, random, re | |
| NAMES = ["Jason", "Kelly", "Daniel", "Rita", "Amy", "Kevin", "Linda", "Peter", "Vivian", "Frank", | |
| "Tom", "Cindy", "Eric", "Grace", "Sam", "Joyce", "Leo", "Nina", "Oscar", "Sandy", "Ryan", | |
| "Emma", "Jack", "Mia", "Henry", "Chloe", "Ivan", "Wendy", "Alan", "Tina"] | |
| SUR = ["王", "陳", "林", "李", "張", "黃", "吳", "劉", "蔡", "楊", "許", "鄭", "謝", "郭", "洪"] | |
| TITLE = ["經理", "助理", "工程師", "專員", "主任", "課長", "副理", "顧問", "店長"] | |
| 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"] | |
| APP = ["App", "Line", "Email", "Portal", "Outlook", "Teams", "Slack", "ERP 系統", "CRM 系統", "官網"] | |
| 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", "行事曆", "購物車", "訂單", "帳號", "密碼", "會員卡", "序號", "授權碼", "點數"] | |
| ACT_EN = ["login", "logout", "update", "reset", "upload", "download", "check", "confirm", "submit", | |
| "cancel", "review", "approve", "sync", "backup", "scan"] | |
| STATUS = ["ready", "done", "updated", "confirmed", "cancelled", "pending", "online", "offline", "expired"] | |
| EVENT = ["meeting", "Zoom 會議", "conference call", "interview", "presentation", "demo", "workshop", "training"] | |
| ADJ = ["busy", "urgent", "important", "ready", "OK", "fine"] | |
| def ext(): return str(random.randint(1000, 9999)) | |
| def num(): return str(random.randint(100000, 999999)) | |
| 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", "明天上午", "後天下午", "這個禮拜五", "下週一早上"]) | |
| def disc(): return random.choice(["九折", "八五折", "七九折", "買一送一", "免運"]) | |
| FRAMES = [ | |
| "您好,{dept}的 {name} {sur}{title}為您服務。", | |
| "幫您轉接給 {name} {sur}{title},他的分機是 {ext}。", | |
| "請問您要查詢的{item}編號是多少?", | |
| "您的{item}已經 {status} 了,請至 {app} 查看。", | |
| "{name} 的 {event} 改到{time}。", | |
| "請至 {app} 點選 {act} 重新登入。", | |
| "我這邊先幫您 {act} 這筆{item}。", | |
| "這個{item}需要重新 {act},麻煩您稍等。", | |
| "您的會員 {status},現在升級 VIP 可享{disc}優惠。", | |
| "麻煩您把 {item} email 到我的信箱,謝謝。", | |
| "系統顯示您的{item}需要 {act},請聯絡{dept}。", | |
| "請問 {name} 在嗎?我這邊有一份 {item} 要給他。", | |
| "您的訂單編號是 {num},預計{time}送達。", | |
| "我幫您預約{time}的 {event},地點在三樓會議室。", | |
| "不好意思,{app} 現在 {status},請您稍後再試。", | |
| "請先 {act} 一下您的{item},我這邊同步處理。", | |
| "{name} 說他今天比較 {adj},{event}可能要延到{time}。", | |
| "您的{item}我已經 {status},等一下會 send 給您。", | |
| "麻煩您提供一下 {item} 的序號,我幫您 {act}。", | |
| "這個 case 我先 update 到系統,{dept}會再回覆您。", | |
| "我的 {item} 今天有點問題,可以幫我 {act} 嗎?", | |
| "請問這個 {event} 的 link 是哪一個?", | |
| "您好,這裡是 {dept},請問需要什麼 service?", | |
| "{name} 的分機 {ext} 現在忙線中,要幫您留言嗎?", | |
| "您的 password 已經過期,請用 {app} 重設一個新的。", | |
| "我這邊收到您的 {item} 了,正在 {act} 中,請稍候。", | |
| "下午的 {event} 我會把 agenda 先寄給大家。", | |
| "麻煩 {name} 在{time}前把{item} {act} 完成。", | |
| "這份{item}的 deadline 是{time},請務必準時。", | |
| "您的 VIP 點數還有 {num} 點,可以折抵{disc}。", | |
| "請問您的 {app} 帳號是用 email 還是手機註冊的?", | |
| "我幫您把{item} upload 到雲端了,連結在 Line 裡面。", | |
| "{name} {sur}{title}稍後會 call 您,大概{time}。", | |
| "您的退款已經 {status},三到五個 working day 會入帳。", | |
| "這台機器的 firmware 要 {act},我請 {name} 過去處理。", | |
| "麻煩您先 confirm 一下{time}的 {event} 方不方便。", | |
| "您的 {item} 目前 {status},如需協助請撥分機 {ext}。", | |
| "我把今天的 meeting note 整理成 PDF 寄給您。", | |
| "請問您要的是 standard 版還是 premium 版的{item}?", | |
| "您好,{name} 的 schedule 我看一下,他{time}有空。", | |
| ] | |
| def fill(frame): | |
| s = frame.format( | |
| name=random.choice(NAMES), sur=random.choice(SUR), title=random.choice(TITLE), | |
| dept=random.choice(DEPT), app=random.choice(APP), item=random.choice(ITEM), | |
| act=random.choice(ACT_EN), status=random.choice(STATUS), event=random.choice(EVENT), | |
| adj=random.choice(ADJ), ext=ext(), num=num(), time=time_(), disc=disc()) | |
| return s | |
| def main(): | |
| ap = argparse.ArgumentParser() | |
| ap.add_argument("--n", type=int, default=2800) | |
| ap.add_argument("--out", default="codemix_corpus.txt") | |
| ap.add_argument("--seed", type=int, default=42) | |
| a = ap.parse_args() | |
| random.seed(a.seed) | |
| out, tries = set(), 0 | |
| while len(out) < a.n and tries < a.n * 40: | |
| tries += 1 | |
| s = fill(random.choice(FRAMES)) | |
| # keep only genuine code-mix (has both Han + ASCII letters) and a sane length | |
| if re.search(r"[一-鿿]", s) and re.search(r"[A-Za-z]", s) and 8 <= len(s) <= 60: | |
| out.add(s) | |
| out = sorted(out) | |
| with open(a.out, "w", encoding="utf-8") as f: | |
| f.write("\n".join(out) + "\n") | |
| print(f"wrote {len(out)} diverse code-mix sentences -> {a.out} (from {len(FRAMES)} frames)") | |
| import random as _r; _r.seed(1) | |
| for s in _r.sample(out, 8): print(" ", s) | |
| if __name__ == "__main__": | |
| main() | |