Upload 6 files

.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
+asha.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,10 @@
 ---
-title: ASHA Assistant
-emoji: 📈
-colorFrom: yellow
-colorTo: purple
+title: Cho Assistant
+emoji: 🌍
+colorFrom: indigo
+colorTo: yellow
 sdk: gradio
-sdk_version: 3.29.0
+sdk_version: 3.28.1
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,124 @@
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import ElasticVectorSearch, Pinecone, Weaviate, FAISS
+
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import OpenAI
+import gradio as gr
+import openai
+import os
+
+from bark import SAMPLE_RATE, generate_audio, preload_models
+from scipy.io.wavfile import write as write_wav
+from IPython.display import Audio
+
+
+api_key = os.getenv('OPENAI_API_KEY')
+openai.api_key = api_key
+
+# connect your Google Drive
+"""from google.colab import drive
+drive.mount('/content/gdrive', force_remount=True)
+root_dir = "/content/gdrive/My Drive/"
+data_path = '/content/gdrive/My Drive/CDSS/LLM Demos/ASHA material'
+"""
+from langchain.document_loaders import PyPDFDirectoryLoader
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.document_loaders import PyPDFLoader
+from langchain.vectorstores import Chroma
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.document_loaders import UnstructuredPDFLoader
+from langchain.llms import OpenAI
+from langchain.chains.question_answering import load_qa_chain
+
+pdf_folder_path = 'ASHAmaterial'
+loader = PyPDFDirectoryLoader(pdf_folder_path)
+
+pages = loader.load_and_split()
+embeddings = OpenAIEmbeddings(openai_api_key ='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')
+docsearch = Chroma.from_documents(pages, embeddings).as_retriever()
+from pydub import AudioSegment
+
+# download and load all models
+preload_models()
+
+
+lang_dict = {
+    "English": "en",
+}
+
+
+# generate audio from text
+text_prompt = """
+     Hello, my name is Suno. And, uh — and I like pizza. [laughs] 
+     But I also have other interests such as playing tic tac toe.
+"""
+#audio_array = generate_audio(text_prompt)
+
+# save audio to disk
+#write_wav("bark_generation.wav", SAMPLE_RATE, audio_array)
+  
+# play text in notebook
+#Audio(audio_array, rate=SAMPLE_RATE)
+
+def get_asr_output(audio_path,lang = 'English'):
+    audio = AudioSegment.from_file(audio_path)
+    audio.export("temp.wav", format="wav")
+    file = open("temp.wav","rb")
+    
+    
+    transcription = openai.Audio.transcribe("whisper-1", file, language=lang)
+    op_text = transcription.text
+
+    """ if lang == "hi":
+        op_text = asr_pipe("temp.wav")['text']
+        print('whisper',transcription)
+        print('ai4b',op_text) """
+    
+    return op_text
+
+def greet(audio, lang, if_audio=True):
+    query = get_asr_output(audio, lang_dict[lang])
+    
+    return query
+
+def greet2(query):
+    
+    docs = docsearch.get_relevant_documents(query)
+    chain = load_qa_chain(OpenAI(temperature=0,openai_api_key ='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' ), chain_type="stuff")
+    answer = chain.run(input_documents=docs, question=query)
+
+    return answer
+
+def get_audio2(answer):
+    audio_array = generate_audio(answer)
+    write_wav("bark_generation.wav", SAMPLE_RATE, audio_array)
+    
+    return 24000, audio_array
+    
+def hello():
+    return "hey"
+def dummy(name):
+    return "bark_generation.wav"
+
+lang = gr.Radio(list(lang_dict.keys()), label="Select a Language")
+
+with gr.Blocks(title="ASHA Saheli") as demo:
+    gr.Image('asha.png', shape = (10,10))
+    lang = gr.Radio(list(lang_dict.keys()), label="Select a Language")
+    user_audio = gr.Audio(source="microphone",type="filepath",label = "Speak your query")
+    text = gr.Textbox(placeholder="Question", name = "Question / Voice Transcription", show_label=False)
+    output = gr.Textbox(placeholder="The answer will appear here", interactive=False, show_label = False)
+    
+    get_text_from_audio = gr.Button("Transcribe")
+    get_text_from_audio.click(greet,[user_audio, lang],[text])
+    
+
+    submit = gr.Button("Submit")
+    submit.click(greet2, [text], [output])
+
+    get_audio = gr.Button('Get Audio')
+    audio = gr.Audio()
+    get_audio.click(get_audio2, output, audio)
+    
+demo.launch()

requirements.txt

@@ -0,0 +1,173 @@
+aiofiles==23.1.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+altair==5.0.0
+anyio==3.6.2
+argilla==1.6.0
+asttokens==2.2.1
+async-timeout==4.0.2
+attrs==23.1.0
+backcall==0.2.0
+backoff==2.2.1
+boto3==1.26.131
+botocore==1.29.131
+certifi==2023.5.7
+cffi==1.15.1
+charset-normalizer==3.1.0
+chromadb==0.3.22
+click==8.1.3
+clickhouse-connect==0.5.23
+cmake==3.26.3
+commonmark==0.9.1
+contourpy==1.0.7
+cryptography==40.0.2
+cycler==0.11.0
+Cython==0.29.34
+dataclasses-json==0.5.7
+decorator==5.1.1
+Deprecated==1.2.13
+duckdb==0.7.1
+einops==0.6.1
+encodec==0.1.1
+et-xmlfile==1.1.0
+executing==1.2.0
+faiss-cpu==1.7.4
+fastapi==0.95.1
+ffmpy==0.3.0
+filelock==3.12.0
+fonttools==4.39.3
+frozenlist==1.3.3
+fsspec==2023.5.0
+funcy==2.0
+gradio==3.29.0
+gradio_client==0.2.2
+greenlet==2.0.2
+h11==0.14.0
+hnswlib==0.7.0
+httpcore==0.16.3
+httptools==0.5.0
+httpx==0.23.3
+huggingface-hub==0.14.1
+idna==3.4
+importlib-metadata==6.6.0
+importlib-resources==5.12.0
+ipython==8.12.2
+jedi==0.18.2
+Jinja2==3.1.2
+jmespath==1.0.1
+joblib==1.2.0
+jsonschema==4.17.3
+kiwisolver==1.4.4
+langchain==0.0.163
+linkify-it-py==2.0.2
+lit==16.0.3
+lxml==4.9.2
+lz4==4.3.2
+Markdown==3.4.3
+markdown-it-py==2.2.0
+MarkupSafe==2.1.2
+marshmallow==3.19.0
+marshmallow-enum==1.5.1
+matplotlib==3.7.1
+matplotlib-inline==0.1.6
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+monotonic==1.6
+mpmath==1.3.0
+msg-parser==1.2.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+networkx==3.1
+nltk==3.8.1
+numexpr==2.8.4
+numpy==1.23.5
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cufft-cu11==10.9.0.58
+nvidia-curand-cu11==10.2.10.91
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-nccl-cu11==2.14.3
+nvidia-nvtx-cu11==11.7.91
+olefile==0.46
+openai==0.27.6
+openapi-schema-pydantic==1.2.4
+openpyxl==3.1.2
+orjson==3.8.12
+packaging==23.1
+pandas==1.5.3
+parso==0.8.3
+pdfminer.six==20221105
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.5.0
+pkgutil_resolve_name==1.3.10
+posthog==3.0.1
+prompt-toolkit==3.0.38
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pycparser==2.21
+pydantic==1.10.7
+pydub==0.25.1
+Pygments==2.15.1
+pypandoc==1.11
+pyparsing==3.0.9
+pypdf==3.8.1
+PyPDF2==3.0.1
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-docx==0.8.11
+python-dotenv==1.0.0
+python-magic==0.4.27
+python-multipart==0.0.6
+python-pptx==0.6.21
+pytz==2023.3
+PyYAML==6.0
+regex==2023.5.5
+requests==2.30.0
+rfc3986==1.5.0
+rich==13.0.1
+s3transfer==0.6.1
+scikit-learn==1.2.2
+scipy==1.10.1
+semantic-version==2.10.0
+sentence-transformers==2.2.2
+sentencepiece==0.1.99
+six==1.16.0
+sniffio==1.3.0
+SQLAlchemy==2.0.12
+stack-data==0.6.2
+starlette==0.26.1
+suno-bark @ git+https://github.com/suno-ai/bark.git@1ad007171e0c46078eb6d3afb6db4daf0c4f41cd
+sympy==1.11.1
+tenacity==8.2.2
+threadpoolctl==3.1.0
+tiktoken==0.4.0
+tokenizers==0.13.3
+toolz==0.12.0
+torch==2.0.1
+torchaudio==2.0.2
+torchvision==0.15.2
+tqdm==4.65.0
+traitlets==5.9.0
+transformers==4.28.1
+triton==2.0.0
+typing-inspect==0.8.0
+typing_extensions==4.5.0
+tzdata==2023.3
+uc-micro-py==1.0.2
+unstructured==0.6.5
+urllib3==1.26.15
+uvicorn==0.22.0
+uvloop==0.17.0
+watchfiles==0.19.0
+wcwidth==0.2.6
+websockets==11.0.3
+wrapt==1.14.1
+XlsxWriter==3.1.0
+yarl==1.9.2
+zipp==3.15.0
+zstandard==0.21.0