Upload folder using huggingface_hub
Browse files- README.md +70 -8
- __pycache__/app.cpython-311.pyc +0 -0
- app.py +266 -0
- requirements.txt +3 -0
README.md
CHANGED
|
@@ -1,13 +1,75 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 6.31.0
|
| 8 |
-
python_version: '3.12'
|
| 9 |
app_file: app.py
|
| 10 |
-
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: PLaMo 3 Translate API
|
| 3 |
+
emoji: 🌐
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: green
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: "6.31.0"
|
|
|
|
| 8 |
app_file: app.py
|
| 9 |
+
python_version: "3.12"
|
| 10 |
+
short_description: PLaMo 3 Translate 2B (PFN) REST & MCP API on ZeroGPU
|
| 11 |
+
startup_duration_timeout: 30m
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# 🌐 PLaMo 3 Translate API
|
| 15 |
+
|
| 16 |
+
[PLaMo 3 Translate](https://huggingface.co/pfnet/plamo-3-translate-2b)(PFN 製・53言語対応の翻訳特化 LLM)を
|
| 17 |
+
ZeroGPU(RTX PRO 6000 Blackwell 48GB)上で動かし、**REST API / MCP サーバ**として叩けるようにした Space です。
|
| 18 |
+
|
| 19 |
+
Built with PLaMo.
|
| 20 |
+
|
| 21 |
+
## Endpoints
|
| 22 |
+
|
| 23 |
+
| Endpoint | Description |
|
| 24 |
+
|---|---|
|
| 25 |
+
| `POST /gradio_api/call/translate` | 1テキスト翻訳 |
|
| 26 |
+
| `POST /gradio_api/call/translate_batch` | JSON 配列の一括翻訳 |
|
| 27 |
+
| `https://<space>.hf.space/gradio/mcp` | MCP サーバ(tools: `translate`, `translate_batch`) |
|
| 28 |
+
|
| 29 |
+
### curl
|
| 30 |
+
|
| 31 |
+
```bash
|
| 32 |
+
curl -s -X POST "https://kouta728-plamo-3-translate-api.hf.space/gradio_api/call/translate" \
|
| 33 |
+
-H "Content-Type: application/json" \
|
| 34 |
+
-d '{"data": ["会議は来週の月曜日に変更されました。", "en", "", "", "", "", "", 512]}'
|
| 35 |
+
# => {"event_id": "<id>"}
|
| 36 |
+
curl -s "https://kouta728-plamo-3-translate-api.hf.space/gradio_api/call/translate/<id>"
|
| 37 |
+
# => {"data": ["The meeting has been rescheduled for next Monday."]}
|
| 38 |
+
```
|
| 39 |
+
|
| 40 |
+
`/translate` の `data` は順に:
|
| 41 |
+
`text, target_lang, source_lang, context, glossary, form, history, max_new_tokens`
|
| 42 |
+
|
| 43 |
+
- `target_lang`: `en`, `ja`, `zh-hans`, ...(53言語コード)
|
| 44 |
+
- `source_lang`: 空欄で自動判定
|
| 45 |
+
- `context`: 文脈(例: 周辺テキスト)
|
| 46 |
+
- `glossary`: `[{"source": "管理画面", "target": "dashboard"}]` 形式の JSON
|
| 47 |
+
- `form`: `plain` / `polite`(`target_lang="ja"` のときのみ)
|
| 48 |
+
- `history`: 過去の `{"source": ..., "translation": ...}` ペアの JSON(段落またぎで訳語を統一)
|
| 49 |
+
- `max_new_tokens`: 最大 4096
|
| 50 |
+
|
| 51 |
+
### Python (gradio_client)
|
| 52 |
+
|
| 53 |
+
```python
|
| 54 |
+
from gradio_client import Client
|
| 55 |
+
|
| 56 |
+
client = Client("https://kouta728-plamo-3-translate-api.hf.space")
|
| 57 |
+
print(client.predict("こんにちは、お元気ですか?", "en", api_name="/translate"))
|
| 58 |
+
# Hello, how are you?
|
| 59 |
+
```
|
| 60 |
+
|
| 61 |
+
## Model
|
| 62 |
+
|
| 63 |
+
- Default: `pfnet/plamo-3-translate-2b` (BF16, 約5.8GB)
|
| 64 |
+
- Change via env var `MODEL_REPO` (e.g. `pfnet/plamo-3-translate-0.8b` / `-8b`; 31B は ZeroGPU `xlarge` が必要)
|
| 65 |
+
|
| 66 |
+
## Runtime notes
|
| 67 |
+
|
| 68 |
+
- ZeroGPU 上で動くため、長時間アクセスがないと Space はスリープします(復帰時はコールドスタートで数分かかることがあります)。
|
| 69 |
+
定期的に ping する keep-alive の Scheduled Job を設定済みです(`hf jobs scheduled ps` で確認)。
|
| 70 |
+
- 翻訳リクエストは呼び出し側アカウントの ZeroGPU 日次クォータ(無料アカウント 5分/日)を消費します。Space 作成者(このアカウント)は無料です。
|
| 71 |
+
|
| 72 |
+
## License
|
| 73 |
+
|
| 74 |
+
Model: [PLaMo Community License](https://plamo.preferredai.jp/info/plamo-community-license-en)
|
| 75 |
+
(個人・非商用利用は無料。商用利用は売上10億円以下なら登録フォームで無料)
|
__pycache__/app.cpython-311.pyc
ADDED
|
Binary file (14.8 kB). View file
|
|
|
app.py
ADDED
|
@@ -0,0 +1,266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""PLaMo 3 Translate API — Gradio Space on ZeroGPU.
|
| 2 |
+
|
| 3 |
+
Exposed endpoints (Gradio auto-generates a REST API + MCP server):
|
| 4 |
+
POST /gradio_api/call/translate -> single text translation
|
| 5 |
+
POST /gradio_api/call/translate_batch -> JSON list of texts
|
| 6 |
+
MCP: https://<space>.hf.space/gradio/mcp
|
| 7 |
+
"""
|
| 8 |
+
|
| 9 |
+
import json
|
| 10 |
+
import os
|
| 11 |
+
|
| 12 |
+
import spaces # noqa: F401 (MUST be imported before torch on ZeroGPU)
|
| 13 |
+
import torch
|
| 14 |
+
import gradio as gr
|
| 15 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 16 |
+
|
| 17 |
+
MODEL_REPO = os.environ.get("MODEL_REPO", "pfnet/plamo-3-translate-2b")
|
| 18 |
+
MAX_NEW_TOKENS_CAP = 4096
|
| 19 |
+
|
| 20 |
+
LANGUAGES = [
|
| 21 |
+
"ja", "en", "zh-hans", "zh-hant", "ko", "ar", "az", "be", "bg", "bn",
|
| 22 |
+
"ca", "ceb", "de", "es", "et", "eu", "fa", "fr", "gu", "he", "hi", "hr",
|
| 23 |
+
"hu", "hy", "id", "it", "jv", "ka", "kk", "km", "lt", "lv", "ml", "mr",
|
| 24 |
+
"ms", "my", "ne", "nl", "pa", "pl", "ru", "si", "sk", "sl", "sr", "sw",
|
| 25 |
+
"ta", "te", "th", "tl", "ur", "uz", "vi",
|
| 26 |
+
]
|
| 27 |
+
|
| 28 |
+
print(f"[boot] loading model: {MODEL_REPO}", flush=True)
|
| 29 |
+
tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO, trust_remote_code=True)
|
| 30 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 31 |
+
MODEL_REPO,
|
| 32 |
+
trust_remote_code=True,
|
| 33 |
+
dtype=torch.bfloat16,
|
| 34 |
+
).to("cuda")
|
| 35 |
+
model.eval()
|
| 36 |
+
print("[boot] model ready", flush=True)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
def _translate_one(
|
| 40 |
+
text: str,
|
| 41 |
+
target_lang: str,
|
| 42 |
+
source_lang: str,
|
| 43 |
+
context: str,
|
| 44 |
+
glossary_json: str,
|
| 45 |
+
form: str,
|
| 46 |
+
history_json: str,
|
| 47 |
+
max_new_tokens: int,
|
| 48 |
+
) -> str:
|
| 49 |
+
messages = []
|
| 50 |
+
if history_json.strip():
|
| 51 |
+
for pair in json.loads(history_json):
|
| 52 |
+
messages.append({"role": "user", "content": pair["source"]})
|
| 53 |
+
messages.append({"role": "assistant", "content": pair["translation"]})
|
| 54 |
+
messages.append({"role": "user", "content": text})
|
| 55 |
+
|
| 56 |
+
template_kwargs = {
|
| 57 |
+
"target_lang": target_lang,
|
| 58 |
+
"add_generation_prompt": True,
|
| 59 |
+
"return_dict": True,
|
| 60 |
+
"return_tensors": "pt",
|
| 61 |
+
}
|
| 62 |
+
if source_lang.strip():
|
| 63 |
+
template_kwargs["source_lang"] = source_lang.strip()
|
| 64 |
+
if context.strip():
|
| 65 |
+
template_kwargs["context"] = context
|
| 66 |
+
if form.strip():
|
| 67 |
+
template_kwargs["form"] = form.strip()
|
| 68 |
+
if glossary_json.strip():
|
| 69 |
+
template_kwargs["glossary"] = json.loads(glossary_json)
|
| 70 |
+
|
| 71 |
+
inputs = tokenizer.apply_chat_template(messages, **template_kwargs).to(model.device)
|
| 72 |
+
prompt_len = inputs["input_ids"].shape[1]
|
| 73 |
+
max_new_tokens = max(16, min(int(max_new_tokens), MAX_NEW_TOKENS_CAP))
|
| 74 |
+
|
| 75 |
+
with torch.inference_mode():
|
| 76 |
+
output = model.generate(**inputs, do_sample=False, max_new_tokens=max_new_tokens)
|
| 77 |
+
return tokenizer.decode(output[0, prompt_len:], skip_special_tokens=True).strip()
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
@spaces.GPU(duration=120)
|
| 81 |
+
def translate(
|
| 82 |
+
text: str,
|
| 83 |
+
target_lang: str = "en",
|
| 84 |
+
source_lang: str = "",
|
| 85 |
+
context: str = "",
|
| 86 |
+
glossary: str = "",
|
| 87 |
+
form: str = "",
|
| 88 |
+
history: str = "",
|
| 89 |
+
max_new_tokens: int = 2048,
|
| 90 |
+
) -> str:
|
| 91 |
+
"""Translate `text` into `target_lang` with PLaMo 3 Translate (PFN).
|
| 92 |
+
|
| 93 |
+
Args:
|
| 94 |
+
text: Source text to translate.
|
| 95 |
+
target_lang: Target language code (e.g. "en", "ja", "zh-hans"). One of 53 supported codes.
|
| 96 |
+
source_lang: Source language code. Empty = auto-detect from the text.
|
| 97 |
+
context: Optional reference context (surrounding text / situation) to disambiguate the translation.
|
| 98 |
+
glossary: Optional JSON list of {"source": ..., "target": ...} term pairs, e.g.
|
| 99 |
+
[{"source": "管理画面", "target": "dashboard"}].
|
| 100 |
+
form: Optional Japanese output style: "plain" or "polite" (only valid with target_lang="ja").
|
| 101 |
+
history: Optional JSON list of previous {"source": ..., "translation": ...} pairs used as
|
| 102 |
+
translation history (keeps terminology/style consistent across paragraphs).
|
| 103 |
+
max_new_tokens: Generation limit for the translation (capped at 4096).
|
| 104 |
+
|
| 105 |
+
Returns:
|
| 106 |
+
The translated text.
|
| 107 |
+
"""
|
| 108 |
+
return _translate_one(
|
| 109 |
+
text, target_lang, source_lang, context, glossary, form, history, max_new_tokens
|
| 110 |
+
)
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
@spaces.GPU(duration=300)
|
| 114 |
+
def translate_batch(
|
| 115 |
+
texts_json: str,
|
| 116 |
+
target_lang: str = "en",
|
| 117 |
+
source_lang: str = "",
|
| 118 |
+
context: str = "",
|
| 119 |
+
glossary: str = "",
|
| 120 |
+
form: str = "",
|
| 121 |
+
max_new_tokens: int = 2048,
|
| 122 |
+
) -> str:
|
| 123 |
+
"""Translate a JSON array of texts into `target_lang` with PLaMo 3 Translate (PFN).
|
| 124 |
+
|
| 125 |
+
Args:
|
| 126 |
+
texts_json: JSON array of source strings, e.g. ["こんにちは。", "お元気ですか?"].
|
| 127 |
+
target_lang: Target language code (e.g. "en", "ja").
|
| 128 |
+
source_lang: Source language code. Empty = auto-detect.
|
| 129 |
+
context: Optional shared reference context applied to every text.
|
| 130 |
+
glossary: Optional JSON list of {"source": ..., "target": ...} term pairs applied to every text.
|
| 131 |
+
form: Optional Japanese output style: "plain" or "polite" (only with target_lang="ja").
|
| 132 |
+
max_new_tokens: Per-text generation limit (capped at 4096).
|
| 133 |
+
|
| 134 |
+
Returns:
|
| 135 |
+
JSON array of translated strings, in the same order as the input.
|
| 136 |
+
"""
|
| 137 |
+
texts = json.loads(texts_json)
|
| 138 |
+
if not isinstance(texts, list) or not all(isinstance(t, str) for t in texts):
|
| 139 |
+
raise ValueError("texts_json must be a JSON array of strings")
|
| 140 |
+
results = [
|
| 141 |
+
_translate_one(t, target_lang, source_lang, context, glossary, form, "", max_new_tokens)
|
| 142 |
+
for t in texts
|
| 143 |
+
]
|
| 144 |
+
return json.dumps(results, ensure_ascii=False)
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
API_DOC = """## REST API
|
| 148 |
+
|
| 149 |
+
Base URL: `https://kouta728-plamo-3-translate-api.hf.space`
|
| 150 |
+
|
| 151 |
+
```bash
|
| 152 |
+
# 1) POST the request
|
| 153 |
+
curl -s -X POST "https://kouta728-plamo-3-translate-api.hf.space/gradio_api/call/translate" \\
|
| 154 |
+
-H "Content-Type: application/json" \\
|
| 155 |
+
-d '{"data": ["会議は来週の月曜日に変更されました。", "en", "", "", "", "", "", 512]}'
|
| 156 |
+
# => {"event_id": "<id>"}
|
| 157 |
+
|
| 158 |
+
# 2) GET the result
|
| 159 |
+
curl -s "https://kouta728-plamo-3-translate-api.hf.space/gradio_api/call/translate/<id>"
|
| 160 |
+
# => {"data": ["The meeting has been rescheduled for next Monday."]}
|
| 161 |
+
```
|
| 162 |
+
|
| 163 |
+
`data` order: `text, target_lang, source_lang, context, glossary, form, history, max_new_tokens`
|
| 164 |
+
|
| 165 |
+
Batch endpoint `/gradio_api/call/translate_batch` takes
|
| 166 |
+
`texts_json, target_lang, source_lang, context, glossary, form, max_new_tokens`.
|
| 167 |
+
|
| 168 |
+
## Python client
|
| 169 |
+
|
| 170 |
+
```python
|
| 171 |
+
from gradio_client import Client
|
| 172 |
+
|
| 173 |
+
client = Client("https://kouta728-plamo-3-translate-api.hf.space")
|
| 174 |
+
print(client.predict("こんにちは、お元気ですか?", "en", api_name="/translate"))
|
| 175 |
+
# Hello, how are you?
|
| 176 |
+
```
|
| 177 |
+
|
| 178 |
+
## MCP
|
| 179 |
+
|
| 180 |
+
The Space is also an MCP server: `https://kouta728-plamo-3-translate-api.hf.space/gradio/mcp`
|
| 181 |
+
(tools: `translate`, `translate_batch`).
|
| 182 |
+
|
| 183 |
+
## Notes
|
| 184 |
+
|
| 185 |
+
- GPU runs on ZeroGPU (RTX PRO 6000 Blackwell, 48 GB). The Space sleeps after long inactivity;
|
| 186 |
+
the first request after a nap includes a cold start.
|
| 187 |
+
- Model: `pfnet/plamo-3-translate-2b` (BF16, 53 languages). Switch size via the `MODEL_REPO`
|
| 188 |
+
env var (e.g. `pfnet/plamo-3-translate-8b`; 31B needs ZeroGPU `xlarge`).
|
| 189 |
+
- License: [PLaMo Community License](https://plamo.preferredai.jp/info/plamo-community-license-en).
|
| 190 |
+
Built with PLaMo.
|
| 191 |
+
"""
|
| 192 |
+
|
| 193 |
+
with gr.Blocks(title="PLaMo 3 Translate API") as demo:
|
| 194 |
+
gr.Markdown("# 🌐 PLaMo 3 Translate API\nPFN の翻訳特化モデル **PLaMo 3 Translate** を ZeroGPU 上で動かす REST / MCP API です(53言語対応)。")
|
| 195 |
+
|
| 196 |
+
with gr.Tab("Translate"):
|
| 197 |
+
with gr.Row():
|
| 198 |
+
with gr.Column():
|
| 199 |
+
text = gr.Textbox(label="Source text", lines=6, placeholder="翻訳したいテキスト")
|
| 200 |
+
target = gr.Dropdown(choices=LANGUAGES, value="en", label="target_lang")
|
| 201 |
+
source = gr.Textbox(label="source_lang(空欄で自動判定)", placeholder="例: ja")
|
| 202 |
+
ctx = gr.Textbox(label="context(任意: 文脈・状況の説明)", lines=2)
|
| 203 |
+
glos = gr.Textbox(
|
| 204 |
+
label='glossary(任意: JSON 例 [{"source":"管理画面","target":"dashboard"}])',
|
| 205 |
+
lines=2,
|
| 206 |
+
)
|
| 207 |
+
form = gr.Dropdown(choices=["", "plain", "polite"], value="", label='form(ja のみ: plain / polite)')
|
| 208 |
+
hist = gr.Textbox(
|
| 209 |
+
label='history(任意: JSON 例 [{"source":"...","translation":"..."}])', lines=2
|
| 210 |
+
)
|
| 211 |
+
mnt = gr.Slider(16, MAX_NEW_TOKENS_CAP, value=2048, step=16, label="max_new_tokens")
|
| 212 |
+
btn = gr.Button("Translate", variant="primary")
|
| 213 |
+
with gr.Column():
|
| 214 |
+
out = gr.Textbox(label="Translation", lines=12)
|
| 215 |
+
btn.click(
|
| 216 |
+
translate,
|
| 217 |
+
[text, target, source, ctx, glos, form, hist, mnt],
|
| 218 |
+
out,
|
| 219 |
+
api_name="/translate",
|
| 220 |
+
)
|
| 221 |
+
text.submit(
|
| 222 |
+
translate,
|
| 223 |
+
[text, target, source, ctx, glos, form, hist, mnt],
|
| 224 |
+
out,
|
| 225 |
+
api_name=None,
|
| 226 |
+
)
|
| 227 |
+
gr.Examples(
|
| 228 |
+
examples=[
|
| 229 |
+
["会議は来週の月曜日に変更されました。", "en", "", "", "", "", "", 512],
|
| 230 |
+
["Hello, how are you?", "ja", "", "", "", "polite", "", 512],
|
| 231 |
+
["かみを切りました。", "en", "", "工作で折り紙を作っています。", "", "", "", 512],
|
| 232 |
+
[
|
| 233 |
+
"プロジェクトの管理画面を開いてください。",
|
| 234 |
+
"en",
|
| 235 |
+
"ja",
|
| 236 |
+
"",
|
| 237 |
+
'[{"source": "管理画面", "target": "dashboard"}, {"source": "プロジェクト", "target": "project"}]',
|
| 238 |
+
"",
|
| 239 |
+
"",
|
| 240 |
+
512,
|
| 241 |
+
],
|
| 242 |
+
],
|
| 243 |
+
inputs=[text, target, source, ctx, glos, form, hist, mnt],
|
| 244 |
+
)
|
| 245 |
+
|
| 246 |
+
with gr.Tab("Batch (API)"):
|
| 247 |
+
b_in = gr.Textbox(label="texts_json", lines=4, value='["こんにちは。", "お元気ですか?"]')
|
| 248 |
+
b_target = gr.Dropdown(choices=LANGUAGES, value="en", label="target_lang")
|
| 249 |
+
b_source = gr.Textbox(label="source_lang(空欄��自動判定)", value="")
|
| 250 |
+
b_ctx = gr.Textbox(label="context(任意)", value="")
|
| 251 |
+
b_glos = gr.Textbox(label="glossary(任意)", value="")
|
| 252 |
+
b_form = gr.Dropdown(choices=["", "plain", "polite"], value="", label="form(ja のみ)")
|
| 253 |
+
b_mnt = gr.Slider(16, MAX_NEW_TOKENS_CAP, value=2048, step=16, label="max_new_tokens")
|
| 254 |
+
b_btn = gr.Button("Translate batch", variant="primary")
|
| 255 |
+
b_out = gr.Textbox(label="結果 (JSON 配列)", lines=8)
|
| 256 |
+
b_btn.click(
|
| 257 |
+
translate_batch,
|
| 258 |
+
[b_in, b_target, b_source, b_ctx, b_glos, b_form, b_mnt],
|
| 259 |
+
b_out,
|
| 260 |
+
api_name="/translate_batch",
|
| 261 |
+
)
|
| 262 |
+
|
| 263 |
+
with gr.Tab("API"):
|
| 264 |
+
gr.Markdown(API_DOC)
|
| 265 |
+
|
| 266 |
+
demo.launch(mcp_server=True)
|
requirements.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
transformers==5.22.2
|
| 2 |
+
accelerate
|
| 3 |
+
numba
|