Add Fill-mask pipline with jmedroberta-base-manbyo-wordpiece model.

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+MANBYO_201907_Dic-utf8.dic filter=lfs diff=lfs merge=lfs -text

MANBYO_201907_Dic-utf8.dic

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2476d813f192bc069fe499c70e03351009c13ed408f786d8f360b3e59e826e41
+size 71728213

app.py

@@ -1,21 +1,51 @@
 import gradio as gr
-from transformers import pipeline
-
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+from transformers import pipeline, AutoTokenizer
 
+##############
+# <Greeting>
 # def greet(name):
 #     return f"Hello {name}!"
 
 # demo = gr.Interface(fn=greet, inputs="text", outputs="text")
 
-def predict(image):
-    predictions = pipeline(image)
-    return {p["label"]: p["score"] for p in predictions}
+
+##############
+# <Hotdog Not Hotdog>
+# pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+
+# def predict(image):
+#     predictions = pipeline(image)
+#     return {p["label"]: p["score"] for p in predictions}
+
+# demo = gr.Interface(
+#     predict,
+#     inputs=gr.inputs.Image(label="Upload hot dog candidate", type="filepath"),
+#     outputs=gr.outputs.Label(num_top_classes=2),
+#     title="Hot Dog? Or Not?"
+# )
+
+tokenizer = AutoTokenizer.from_pretrained("alabnii/jmedroberta-base-manbyo-wordpiece", **{
+    "mecab_kwargs": {
+        "mecab_option": "-u MANBYO_201907_Dic-utf8.dic"
+    }
+})
+
+pipeline = pipeline(
+    "fill-mask",
+    model="alabnii/jmedroberta-base-manbyo-wordpiece",
+    tokenizer=tokenizer,
+    top_k=20
+)
+
+def fill(text):
+    filled = pipeline(text)
+    return {x["token_str"]: x["score"] for x in filled}
 
 demo = gr.Interface(
-    predict,
-    inputs=gr.inputs.Image(label="Upload hot dog candidate", type="filepath"),
-    outputs=gr.outputs.Label(num_top_classes=2),
-    title="Hot Dog? Or Not?"
+    fill,
+    inputs="text",
+    outputs=gr.Label(label="Output"),
+    title="fill-mask",
+    examples=[['この患者は[MASK]と診断された。']]
 )
 demo.launch()

requirements.txt

@@ -18,6 +18,7 @@ filelock==3.10.7
 fonttools==4.39.3
 frozenlist==1.3.3
 fsspec==2023.3.0
+fugashi==1.2.1
 gradio==3.24.0
 gradio_client==0.0.5
 h11==0.14.0
@@ -26,6 +27,7 @@ httpx==0.23.3
 huggingface-hub==0.13.3
 idna==3.4
 importlib-resources==5.12.0
+ipadic==1.0.0
 Jinja2==3.1.2
 jsonschema==4.17.3
 kiwisolver==1.4.4