Spaces:
Running
Running
| from googletrans import Translator | |
| import spacy | |
| import gradio as gr | |
| spacy.cli.download("en_core_web_sm") | |
| nlp = spacy.load('en_core_web_sm') | |
| translator = Translator() | |
| def Sentencechunker(sentence): | |
| Sentchunks = sentence.split(" ") | |
| chunks = [] | |
| for i in range(len(Sentchunks)): | |
| chunks.append(" ".join(Sentchunks[:i+1])) | |
| return " | ".join(chunks) | |
| def ReverseSentenceChunker(sentence): | |
| reversed_sentence = " ".join(reversed(sentence.split())) | |
| chunks = Sentencechunker(reversed_sentence) | |
| return chunks | |
| def three_words_chunk(sentence): | |
| words = sentence.split() | |
| chunks = [words[i:i+3] for i in range(len(words)-2)] | |
| chunks = [" ".join(chunk) for chunk in chunks] | |
| return " | ".join(chunks) | |
| def keep_nouns_verbs(sentence): | |
| doc = nlp(sentence) | |
| nouns_verbs = [] | |
| for token in doc: | |
| if token.pos_ in ['NOUN','VERB','PUNCT']: | |
| nouns_verbs.append(token.text) | |
| return " ".join(nouns_verbs) | |
| def unique_word_count(text="", state=None): | |
| if state is None: | |
| state = {} | |
| words = text.split() | |
| word_counts = state | |
| for word in words: | |
| if word in word_counts: | |
| word_counts[word] += 1 | |
| else: | |
| word_counts[word] = 1 | |
| sorted_word_counts = sorted(word_counts.items(), key=lambda x: x[1], reverse=True) | |
| return sorted_word_counts, | |
| """ | |
| sentence = "Please help me create a sentence chunker" | |
| sentencechunks = Sentencechunker(sentence) | |
| reversed_chunks = ReverseSentenceChunker(sentence) | |
| TWchunks = three_words_chunk(sentence) | |
| nouns_verbs = keep_nouns_verbs(sentence) | |
| """ | |
| # Translate from English to French | |
| langdest = gr.Dropdown(choices=["af", "de", "es", "ko", "ja", "zh-cn"], label="Choose Language", value="de") | |
| """ | |
| def VarTrans(text, langdest): | |
| translated = translator.translate(text, dest=langdest) | |
| SCtranslated = translator.translate(sentencechunks, dest=langdest) | |
| RCtranslated = translator.translate(reversed_chunks, dest=langdest) | |
| TWCtranslated = translator.translate(TWchunks, dest=langdest) | |
| return translated, SCtranslated, RCtranslated, TWCtranslated | |
| """ | |
| ChunkModeDrop = gr.Dropdown(choices=["Chunks", "Reverse", "Three Word Chunks"], label="Choose Chunk Type") | |
| def FrontRevSentChunk (Chunkmode, Translate, Text, langdest): | |
| FinalOutput = "" | |
| TransFinalOutput = "" | |
| if Chunkmode=="Chunks": | |
| FinalOutput += Sentencechunker(Text) | |
| if Chunkmode=="Reverse": | |
| FinalOutput += ReverseSentenceChunker(Text) | |
| if Chunkmode=="Three Word Chunks": | |
| FinalOutput += three_words_chunk(Text) | |
| if Translate: | |
| TransFinalOutput = FinalOutput | |
| translated = translator.translate(TransFinalOutput, dest=langdest) | |
| FinalOutput += "\n" + translated.text | |
| return FinalOutput | |
| """ | |
| print(translated.text) | |
| print(sentencechunks) | |
| print(SCtranslated.text) | |
| print(reversed_chunks) | |
| print(RCtranslated.text) | |
| print(TWchunks) | |
| print(TWCtranslated.text) | |
| print(nouns_verbs) | |
| """ | |
| def Wordchunker(word): | |
| chunks = [] | |
| for i in range(len(word)): | |
| chunks.append(word[:i+1]) | |
| return chunks | |
| word = "please" | |
| wordchunks = Wordchunker(word) | |
| print("\n") | |
| print(wordchunks) | |
| #random_chunk_display(TWCtranslated.text) | |
| with gr.Blocks() as lliface: | |
| gr.HTML("<p> Still Undercontruction </p> <> Arrows app json creator for easy knowledge graphing and spacy POS graph? </p> <p> https://huggingface.co/spaces/RASMUS/Whisper-youtube-crosslingual-subtitles, https://huggingface.co/spaces/vumichien/whisper-speaker-diarization, Maybe duplicate these, private them and then load into spaces? --> Whisper space for youtube, Clip Interrogator, load here and all my random functions esp. text to HTML </p>") | |
| gr.Interface(fn=FrontRevSentChunk, inputs=[ChunkModeDrop, "checkbox", "text", langdest], outputs="text") | |
| gr.Interface(fn=keep_nouns_verbs, inputs=["text"], outputs="text", title="Noun and Verbs only (Plus punctuation") | |
| gr.HTML("Add a codepen pen page here") | |
| gr.Interface(fn=unique_word_count, inputs="text", outputs="text", title="Wordcounter") | |
| lliface.launch() |