add

bart-large-mnli/app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import pipeline
+
+
+sentimentPipeline = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
+def sentiment_analysis(text, labels):
+    candidate_labels = labels.split(',') 
+    results = sentimentPipeline(text, candidate_labels)
+
+    total_results = ""
+    index = 0
+
+    for candidate_label in candidate_labels:
+        total_results += f"Sentiment: {results.get('labels')[index]}, Score: {results.get('scores')[index]}"
+        total_results += '\r\n'
+        index += 1
+
+    return total_results
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs=[
+                        gr.components.Textbox(label="Text"),
+                        gr.components.Textbox(label="Label")
+                    ],
+                    outputs='text',
+                    examples=[['I have a problem with my iphone that needs to be resolved asap!!', 'urgent, not urgent, phone, tablet, computer'], ['Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.', 'mobile, website, billing, account access']],
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

bert-base-uncased/app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from transformers import pipeline
+
+
+unmasker = pipeline('fill-mask', model='bert-base-uncased')
+
+def sentiment_analysis(text):
+    results = unmasker(text)
+    total_results = ""
+
+    for result in results:
+        total_results += f"Token: {result.get('token_str')}, Score: {result.get('score')}"
+        total_results += '\r\n'
+
+    return total_results
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs='text',
+                    outputs='text',
+                    examples=[['Paris is the [MASK] of France.'], ['The goal of life is [MASK].']],
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

bertweet-base-sentiment-analysis/app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+from transformers import pipeline, AutoTokenizer, AutoConfig, AutoModelForSequenceClassification
+
+modelName="finiteautomata/bertweet-base-sentiment-analysis"
+sentimentPipeline = pipeline("sentiment-analysis", model=modelName)
+
+def sentiment_analysis(text):
+    results = sentimentPipeline(text)
+
+    return f"Sentiment: {results[0].get('label')}, Score: {results[0].get('score'):.2f}" 
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs='text', 
+                    outputs='text',
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

deberta-large-mnli-zero-cls/app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import pipeline
+
+
+sentimentPipeline = pipeline("zero-shot-classification", model="Narsil/deberta-large-mnli-zero-cls")
+
+def sentiment_analysis(text, labels):
+    candidate_labels = labels.split(',') 
+    results = sentimentPipeline(text, candidate_labels)
+
+    total_results = ""
+    index = 0
+
+    for candidate_label in candidate_labels:
+        total_results += f"Sentiment: {results.get('labels')[index]}, Score: {results.get('scores')[index]}"
+        total_results += '\r\n'
+        index += 1
+
+    return total_results
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs=[
+                        gr.components.Textbox(label="Text"),
+                        gr.components.Textbox(label="Label")
+                    ],
+                    outputs='text',
+                    examples=[['I have a problem with my iphone that needs to be resolved asap!!', 'urgent, not urgent, phone, tablet, computer'], ['Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.', 'mobile, website, billing, account access']],
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

distilbart-mnli-12-1/app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import pipeline
+
+
+sentimentPipeline = pipeline("zero-shot-classification", model="valhalla/distilbart-mnli-12-1")
+
+def sentiment_analysis(text, labels):
+    candidate_labels = labels.split(',') 
+    results = sentimentPipeline(text, candidate_labels)
+
+    total_results = ""
+    index = 0
+
+    for candidate_label in candidate_labels:
+        total_results += f"Sentiment: {results.get('labels')[index]}, Score: {results.get('scores')[index]}"
+        total_results += '\r\n'
+        index += 1
+
+    return total_results
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs=[
+                        gr.components.Textbox(label="Text"),
+                        gr.components.Textbox(label="Label")
+                    ],
+                    outputs='text',
+                    examples=[['I have a problem with my iphone that needs to be resolved asap!!', 'urgent, not urgent, phone, tablet, computer'], ['Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.', 'mobile, website, billing, account access']],
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

distilbart-mnli-12-3/app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import pipeline
+
+
+sentimentPipeline = pipeline("zero-shot-classification", model="valhalla/distilbart-mnli-12-3")
+
+def sentiment_analysis(text, labels):
+    candidate_labels = labels.split(',') 
+    results = sentimentPipeline(text, candidate_labels)
+
+    total_results = ""
+    index = 0
+
+    for candidate_label in candidate_labels:
+        total_results += f"Sentiment: {results.get('labels')[index]}, Score: {results.get('scores')[index]}"
+        total_results += '\r\n'
+        index += 1
+
+    return total_results
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs=[
+                        gr.components.Textbox(label="Text"),
+                        gr.components.Textbox(label="Label")
+                    ],
+                    outputs='text',
+                    examples=[['I have a problem with my iphone that needs to be resolved asap!!', 'urgent, not urgent, phone, tablet, computer'], ['Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.', 'mobile, website, billing, account access']],
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

distilbert-base-uncased-mnli/app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import pipeline
+
+
+sentimentPipeline = pipeline("zero-shot-classification", model="typeform/distilbert-base-uncased-mnli")
+
+def sentiment_analysis(text, labels):
+    candidate_labels = labels.split(',') 
+    results = sentimentPipeline(text, candidate_labels)
+
+    total_results = ""
+    index = 0
+
+    for candidate_label in candidate_labels:
+        total_results += f"Sentiment: {results.get('labels')[index]}, Score: {results.get('scores')[index]}"
+        total_results += '\r\n'
+        index += 1
+
+    return total_results
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs=[
+                        gr.components.Textbox(label="Text"),
+                        gr.components.Textbox(label="Label")
+                    ],
+                    outputs='text',
+                    examples=[['I have a problem with my iphone that needs to be resolved asap!!', 'urgent, not urgent, phone, tablet, computer'], ['Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.', 'mobile, website, billing, account access']],
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

nli-distilroberta-base/app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from transformers import pipeline
+
+
+sentimentPipeline = pipeline("zero-shot-classification", model="cross-encoder/nli-distilroberta-base")
+
+def sentiment_analysis(text, labels):
+    candidate_labels = labels.split(',') 
+    results = sentimentPipeline(text, candidate_labels)
+
+    total_results = ""
+    index = 0
+
+    for candidate_label in candidate_labels:
+        total_results += f"Sentiment: {results.get('labels')[index]}, Score: {results.get('scores')[index]}"
+        total_results += '\r\n'
+        index += 1
+
+    return total_results
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs=[
+                        gr.components.Textbox(label="Text"),
+                        gr.components.Textbox(label="Label")
+                    ],
+                    outputs='text',
+                    examples=[['Apple just announced the newest iPhone X', 'technology, sports, politics'], ['Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.', 'mobile, website, billing, account access']],
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

roberta-large-mnli/app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from transformers import pipeline
+
+
+sentimentPipeline = pipeline('zero-shot-classification', model='roberta-large-mnli')
+
+def sentiment_analysis(text, labels):
+    candidate_labels = labels.split(',') 
+    results = sentimentPipeline(text, candidate_labels)
+    total_results = ""
+    index = 0
+
+    for candidate_label in candidate_labels:
+        total_results += f"Sentiment: {results.get('labels')[index]}, Score: {results.get('scores')[index]}"
+        total_results += '\r\n'
+        index += 1
+
+    return total_results
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs=[
+                        gr.components.Textbox(label="Text"),
+                        gr.components.Textbox(label="Label")
+                    ],
+                    outputs='text',
+                    examples=[['I am happy', 'negative, netural, positive'], ['I am sad', 'negative, netural, positive']],
+                    title = "文本情感分析"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)

xlm-roberta-base-language-detection/app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+from transformers import pipeline, AutoTokenizer, AutoConfig, AutoModelForSequenceClassification
+
+modelName="papluca/xlm-roberta-base-language-detection"
+sentimentPipeline = pipeline("sentiment-analysis", modelName)
+
+def sentiment_analysis(text):
+    results = sentimentPipeline(text)
+    return results
+    #return f"Sentiment: {results[0].get('label')}, Score: {results[0].get('score'):.2f}" 
+    
+demo = gr.Interface(fn=sentiment_analysis, 
+                    inputs='text', 
+                    outputs='text',
+                    title = "语种分类"
+                    )
+
+
+if __name__ == "__main__":
+    demo.queue(concurrency_count=3)
+    demo.launch(server_name = "0.0.0.0", server_port = 7028)