Reynold97 commited on
Commit
3f2dca0
1 Parent(s): b34759c

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. .gitignore +163 -0
  2. README.md +2 -8
  3. app.py +21 -0
  4. llm.py +25 -0
  5. requirements.txt +0 -0
  6. tts.py +42 -0
.gitignore ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[cod]
4
+ *$py.class
5
+
6
+ # C extensions
7
+ *.so
8
+
9
+ # Distribution / packaging
10
+ .Python
11
+ build/
12
+ develop-eggs/
13
+ dist/
14
+ downloads/
15
+ eggs/
16
+ .eggs/
17
+ lib/
18
+ lib64/
19
+ parts/
20
+ sdist/
21
+ var/
22
+ wheels/
23
+ share/python-wheels/
24
+ *.egg-info/
25
+ .installed.cfg
26
+ *.egg
27
+ MANIFEST
28
+
29
+ # PyInstaller
30
+ # Usually these files are written by a python script from a template
31
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
32
+ *.manifest
33
+ *.spec
34
+
35
+ # Installer logs
36
+ pip-log.txt
37
+ pip-delete-this-directory.txt
38
+
39
+ # Unit test / coverage reports
40
+ htmlcov/
41
+ .tox/
42
+ .nox/
43
+ .coverage
44
+ .coverage.*
45
+ .cache
46
+ nosetests.xml
47
+ coverage.xml
48
+ *.cover
49
+ *.py,cover
50
+ .hypothesis/
51
+ .pytest_cache/
52
+ cover/
53
+
54
+ # Translations
55
+ *.mo
56
+ *.pot
57
+
58
+ # Django stuff:
59
+ *.log
60
+ local_settings.py
61
+ db.sqlite3
62
+ db.sqlite3-journal
63
+
64
+ # Flask stuff:
65
+ instance/
66
+ .webassets-cache
67
+
68
+ # Scrapy stuff:
69
+ .scrapy
70
+
71
+ # Sphinx documentation
72
+ docs/_build/
73
+
74
+ # PyBuilder
75
+ .pybuilder/
76
+ target/
77
+
78
+ # Jupyter Notebook
79
+ .ipynb_checkpoints
80
+
81
+ # IPython
82
+ profile_default/
83
+ ipython_config.py
84
+
85
+ # pyenv
86
+ # For a library or package, you might want to ignore these files since the code is
87
+ # intended to run in multiple environments; otherwise, check them in:
88
+ # .python-version
89
+
90
+ # pipenv
91
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
92
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
93
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
94
+ # install all needed dependencies.
95
+ #Pipfile.lock
96
+
97
+ # poetry
98
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
99
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
100
+ # commonly ignored for libraries.
101
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
102
+ #poetry.lock
103
+
104
+ # pdm
105
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
106
+ #pdm.lock
107
+ # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
108
+ # in version control.
109
+ # https://pdm.fming.dev/#use-with-ide
110
+ .pdm.toml
111
+
112
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
113
+ __pypackages__/
114
+
115
+ # Celery stuff
116
+ celerybeat-schedule
117
+ celerybeat.pid
118
+
119
+ # SageMath parsed files
120
+ *.sage.py
121
+
122
+ # Environments
123
+ .env
124
+ .venv
125
+ env/
126
+ venv/
127
+ ENV/
128
+ env.bak/
129
+ venv.bak/
130
+
131
+ # Spyder project settings
132
+ .spyderproject
133
+ .spyproject
134
+
135
+ # Rope project settings
136
+ .ropeproject
137
+
138
+ # mkdocs documentation
139
+ /site
140
+
141
+ # mypy
142
+ .mypy_cache/
143
+ .dmypy.json
144
+ dmypy.json
145
+
146
+ # Pyre type checker
147
+ .pyre/
148
+
149
+ # pytype static type analyzer
150
+ .pytype/
151
+
152
+ # Cython debug symbols
153
+ cython_debug/
154
+
155
+ # PyCharm
156
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
157
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
158
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
159
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
160
+ #.idea/
161
+
162
+ *.wav
163
+ *.mp3
README.md CHANGED
@@ -1,12 +1,6 @@
1
  ---
2
- title: Sports Analyzer
3
- emoji: 🐢
4
- colorFrom: indigo
5
- colorTo: pink
6
  sdk: gradio
7
  sdk_version: 4.31.5
8
- app_file: app.py
9
- pinned: false
10
  ---
11
-
12
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
+ title: sports-analyzer
3
+ app_file: app.py
 
 
4
  sdk: gradio
5
  sdk_version: 4.31.5
 
 
6
  ---
 
 
app.py ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+
3
+ from tts import transcribe_audio
4
+ from llm import analyze_snippet
5
+
6
+ def pipeline(audio_path):
7
+ """Pipeline to comunicate tts and kg modules"""
8
+ transcription = transcribe_audio(audio_path)
9
+ bullet_points = analyze_snippet(str(transcription))
10
+ return f"Game Analysis:\n {bullet_points}"
11
+
12
+
13
+ iface = gr.Interface(
14
+ fn=pipeline,
15
+ inputs=gr.Audio(sources="microphone", type="filepath", format="wav"),
16
+ outputs="text",
17
+ title="Sports-Analyzer",
18
+ )
19
+
20
+ if __name__ == "__main__":
21
+ iface.launch()
llm.py ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from openai import OpenAI
2
+ import os
3
+ from dotenv import load_dotenv
4
+
5
+ load_dotenv()
6
+
7
+ client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
8
+
9
+ syst_prompt = """
10
+ 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\
11
+ a live game based on poor radio transcriptions snippets. I only want to know important events, actions, player names, team matchup in bullet points,\
12
+ with just a few words, as short and concise as possible, that MUST be your answer and nothing else.\
13
+ """
14
+
15
+ def analyze_snippet(transcription_chunk:str):
16
+ completion = client.chat.completions.create(
17
+ model="gpt-4o",
18
+ messages=[
19
+ {"role": "system", "content": syst_prompt},
20
+ {"role": "user", "content": f"Here is the transcription snippet:{transcription_chunk}"}
21
+ ]
22
+ )
23
+ return completion.choices[0].message.content
24
+
25
+
requirements.txt ADDED
Binary file (92 Bytes). View file
 
tts.py ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os
2
+ import shutil
3
+ from datetime import datetime
4
+ from dotenv import load_dotenv
5
+ from deepgram import DeepgramClient, PrerecordedOptions
6
+
7
+ load_dotenv()
8
+ API_KEY = os.getenv('DEEPGRAM_API_KEY')
9
+ deepgram = DeepgramClient(API_KEY)
10
+
11
+ def ensure_dir(directory):
12
+ """Ensure the specified directory exists; if not, create it."""
13
+ if not os.path.exists(directory):
14
+ os.makedirs(directory)
15
+
16
+ def transcribe_audio(audio_path):
17
+ """Transcribes audio using Deepgram's API and saves the audio file with a unique timestamp."""
18
+ try:
19
+ audio_storage_dir = "permanent_audio_files"
20
+ ensure_dir(audio_storage_dir)
21
+
22
+ # Generate a unique filename with a timestamp
23
+ timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
24
+ filename = f"audio_{timestamp}.wav"
25
+ permanent_audio_path = os.path.join(audio_storage_dir, filename)
26
+
27
+ shutil.copy(audio_path, permanent_audio_path)
28
+ print(f"Saved audio file to: {permanent_audio_path}") # Debug: Confirm file save
29
+
30
+ options = PrerecordedOptions(model="nova-2", smart_format=True, language="en-AU")
31
+
32
+ # Open the permanently stored audio file for transcription
33
+ with open(permanent_audio_path, 'rb') as audio:
34
+ source = {'buffer': audio}
35
+ response = deepgram.listen.prerecorded.v("1").transcribe_file(source, options)
36
+ transcript = response['results']['channels'][0]['alternatives'][0]['transcript']
37
+ return transcript
38
+ except Exception as e:
39
+ print("Error during transcription:", e)
40
+ raise e
41
+ return str(e)
42
+