Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1,163 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+*.wav
+*.mp3

README.md

@@ -1,12 +1,6 @@
 ---
-title: Sports Analyzer
-emoji: 🐢
-colorFrom: indigo
-colorTo: pink
+title: sports-analyzer
+app_file: app.py
 sdk: gradio
 sdk_version: 4.31.5
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+
+from tts import transcribe_audio
+from llm import analyze_snippet
+
+def pipeline(audio_path):
+    """Pipeline to comunicate tts and kg modules"""
+    transcription = transcribe_audio(audio_path)
+    bullet_points = analyze_snippet(str(transcription))
+    return f"Game Analysis:\n {bullet_points}"
+
+
+iface = gr.Interface(
+    fn=pipeline,
+    inputs=gr.Audio(sources="microphone", type="filepath", format="wav"),
+    outputs="text",
+    title="Sports-Analyzer",
+)
+
+if __name__ == "__main__":
+    iface.launch()

llm.py

@@ -0,0 +1,25 @@
+from openai import OpenAI
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
+syst_prompt = """
+You are an expert sports analyzer with more than 10 years of experience in Australian rugby. Your current task is to help me to understand\
+a live game based on poor radio transcriptions snippets. I only want to know important events, actions, player names, team matchup in bullet points,\
+with just a few words, as short and concise as possible, that MUST be your answer and nothing else.\
+"""
+
+def analyze_snippet(transcription_chunk:str):
+    completion = client.chat.completions.create(
+    model="gpt-4o",
+    messages=[
+        {"role": "system", "content": syst_prompt},
+        {"role": "user", "content": f"Here is the transcription snippet:{transcription_chunk}"}
+    ]
+    )
+    return completion.choices[0].message.content
+
+

tts.py

@@ -0,0 +1,42 @@
+import os
+import shutil
+from datetime import datetime
+from dotenv import load_dotenv
+from deepgram import DeepgramClient, PrerecordedOptions
+
+load_dotenv()
+API_KEY = os.getenv('DEEPGRAM_API_KEY')
+deepgram = DeepgramClient(API_KEY) 
+
+def ensure_dir(directory):
+    """Ensure the specified directory exists; if not, create it."""
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+
+def transcribe_audio(audio_path):
+    """Transcribes audio using Deepgram's API and saves the audio file with a unique timestamp."""
+    try:
+        audio_storage_dir = "permanent_audio_files"
+        ensure_dir(audio_storage_dir)
+        
+        # Generate a unique filename with a timestamp
+        timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
+        filename = f"audio_{timestamp}.wav"
+        permanent_audio_path = os.path.join(audio_storage_dir, filename)
+        
+        shutil.copy(audio_path, permanent_audio_path)
+        print(f"Saved audio file to: {permanent_audio_path}")  # Debug: Confirm file save
+
+        options = PrerecordedOptions(model="nova-2", smart_format=True, language="en-AU")
+    
+        # Open the permanently stored audio file for transcription
+        with open(permanent_audio_path, 'rb') as audio:
+            source = {'buffer': audio}
+            response = deepgram.listen.prerecorded.v("1").transcribe_file(source, options)
+            transcript = response['results']['channels'][0]['alternatives'][0]['transcript']
+            return transcript
+    except Exception as e:
+        print("Error during transcription:", e)
+        raise e
+        return str(e)
+