import streamlit as st import time from transformers import pipeline from datasets import load_dataset, Audio st.set_page_config(page_title="🤗 Transformers Library examples",layout="wide") st.title('🤗 :rainbow[Transformers Library examples]') # Done # function for Sentiment Analysis or Text classification model def sentiment_analysis(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") st.write("Output:") st.success(results) st.divider() st.subheader("Example: Multiple statements analysis") with st.spinner('Wait for it...'): time.sleep(5) code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier([ "This is quick tutorial site.", "I learnt new topics today.", "I do not like lengthy tutorials." ]) ''' st.code(code, language='python') results = classifier([ "This is quick tutorial site.", "I learnt new topics today.", "I do not like lengthy tutorials." ]) st.write("Output:") st.success(results) # function for Sentiment Analysis or Text classification model def text_generation(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") # function for Sentiment Analysis or Text classification model def summarization(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") # DONE # function for Image Classification model def image_classification(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): st.image("./data/dog.jpeg", width=250, use_column_width=100) with st.spinner('Wait for it...'): time.sleep(8) vision_classifier = pipeline(model="google/vit-base-patch16-224") preds = vision_classifier(images="./data/dog.jpeg") st.success("Output:") st.json(preds) # function for Sentiment Analysis or Text classification model def image_segmentation(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") # function for Sentiment Analysis or Text classification model def object_detection(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") # function for Audio Classification model def audio_classification(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") # function forAutomatic Speech Recognition model def automatic_speech_recognition(): minds = load_dataset("PolyAI/minds14", name="en-US", split="train") minds = minds.train_test_split(test_size=0.2) st.write(minds) minds = minds.remove_columns(["path", "transcription", "english_transcription", "lang_id"]) st.write("minds[train][0] " , minds["train"][0]) labels = minds["train"].features["intent_class"].names st.write("labels " ,labels) label2id, id2label = dict(), dict() for i, label in enumerate(labels): label2id[label] = str(i) id2label[str(i)] = label st.write("label2id - id2label" , label2id , id2label) code = ''' from transformers import pipeline classifier = pipeline("automatic-speech-recognition") results = transcriber("./data/mlk.flac") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) transcriber = pipeline(task="automatic-speech-recognition") results = transcriber("./data/audio.m4a") st.write("Output:") st.success(results) # function for Image Captioningn model def image_captioning(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") # function for Mask Filling model def mask_filling(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") # function for Document Question Answering model def document_question_answering(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') with st.spinner('Wait for it...'): time.sleep(5) # function for Named Entity Recognition model def named_entity_recognition(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") # function for translation model def translation(): code = ''' from transformers import pipeline classifier = pipeline("sentiment-analysis") results = classifier("Transformers library is very helpful.") ''' st.code(code, language='python') if st.button("Run Test ", type="primary"): with st.spinner('Wait for it...'): time.sleep(5) classifier = pipeline("sentiment-analysis") col1, col2 = st.columns(2) ''' - `"audio-classification"`: will return a [`AudioClassificationPipeline`]. - `"automatic-speech-recognition"`: will return a [`AutomaticSpeechRecognitionPipeline`]. - `"conversational"`: will return a [`ConversationalPipeline`]. - `"depth-estimation"`: will return a [`DepthEstimationPipeline`]. - `"document-question-answering"`: will return a [`DocumentQuestionAnsweringPipeline`]. - `"feature-extraction"`: will return a [`FeatureExtractionPipeline`]. - `"fill-mask"`: will return a [`FillMaskPipeline`]:. - `"image-classification"`: will return a [`ImageClassificationPipeline`]. - `"image-feature-extraction"`: will return an [`ImageFeatureExtractionPipeline`]. - `"image-segmentation"`: will return a [`ImageSegmentationPipeline`]. - `"image-to-image"`: will return a [`ImageToImagePipeline`]. - `"image-to-text"`: will return a [`ImageToTextPipeline`]. - `"mask-generation"`: will return a [`MaskGenerationPipeline`]. - `"object-detection"`: will return a [`ObjectDetectionPipeline`]. - `"question-answering"`: will return a [`QuestionAnsweringPipeline`]. - `"summarization"`: will return a [`SummarizationPipeline`]. - `"table-question-answering"`: will return a [`TableQuestionAnsweringPipeline`]. - `"text2text-generation"`: will return a [`Text2TextGenerationPipeline`]. - `"text-classification"` (alias `"sentiment-analysis"` available): will return a [`TextClassificationPipeline`]. - `"text-generation"`: will return a [`TextGenerationPipeline`]:. - `"text-to-audio"` (alias `"text-to-speech"` available): will return a [`TextToAudioPipeline`]:. - `"token-classification"` (alias `"ner"` available): will return a [`TokenClassificationPipeline`]. - `"translation"`: will return a [`TranslationPipeline`]. - `"translation_xx_to_yy"`: will return a [`TranslationPipeline`]. - `"video-classification"`: will return a [`VideoClassificationPipeline`]. - `"visual-question-answering"`: will return a [`VisualQuestionAnsweringPipeline`]. - `"zero-shot-classification"`: will return a [`ZeroShotClassificationPipeline`]. - `"zero-shot-image-classification"`: will return a [`ZeroShotImageClassificationPipeline`]. - `"zero-shot-audio-classification"`: will return a [`ZeroShotAudioClassificationPipeline`]. - `"zero-shot-object-detection"`: will return a [`ZeroShotObjectDetectionPipeline`]. ''' with col1: taskType = st.radio( "Select a type of task to perform", [ "Sentiment Analysis or Text classification", "Text Generation", "Summarization", "Image Classification", "Image Segmentation", "Object Detection", "Audio Classification", "Automatic Speech Recognition", "Visual Question Answering", "Document Question Answering", "Image Captioning", "Mask Filling", "Named Entity Recognition", "Translation" ], captions = [ "**pipeline(task=“sentiment-analysis”)**", "pipeline(task=“text-generation”)", "pipeline(task=“summarization”)", "pipeline(task=“image-classification”)", "pipeline(task=“image-segmentation”)", "pipeline(task=“object-detection”)", "pipeline(task=“audio-classification”)", "pipeline(task=“automatic-speech-recognition”)", "pipeline(task=“vqa”)", "pipeline(task=“document-question-answering”)", "pipeline(task=“image-to-text”)" "Mask Filling", "Named Entity Recognition", "Translation" ], index=0) with col2: st.subheader(f"Example: {taskType}") if taskType == "Sentiment Analysis or Text classification": sentiment_analysis() if taskType == "Text Generation": text_generation() if taskType == "Summarization": summarization() if taskType == "Image Classification": image_classification() if taskType == "Image Segmentation": image_segmentation() if taskType == "Object Detection": object_detection() if taskType == "Audio Classification": audio_classification() if taskType == "Automatic Speech Recognition": automatic_speech_recognition() if taskType == "Document Question Answering": document_question_answering() if taskType == "Image Captioning": image_captioning() if taskType == "Mask Filling": mask_filling() if taskType == "Named Entity Recognition": named_entity_recognition() if taskType == "Translation": translation()