Upload 4 files

Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.12-slim
+
+WORKDIR /usr/src/app
+COPY . .
+
+RUN apt-get update && apt-get install -y git
+# Install dependencies from requirements.txt
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+#RUN pip3 uninstall gradio_client
+
+#RUN pip3 install https://gradio-pypi-previews.s3.amazonaws.com/4bc495cb68aec014cffffce16c14ee1ddaacf7a3/gradio-4.41.0-py3-none-any.whl
+#RUN pip3 install "gradio-client @ git+https://github.com/gradio-app/gradio@4bc495cb68aec014cffffce16c14ee1ddaacf7a3#subdirectory=client/python"
+
+# Expose the port for Gradio
+EXPOSE 7860
+
+# Set the Gradio server name
+ENV GRADIO_SERVER_NAME="0.0.0.0"
+
+# Run the application
+CMD ["python", "-u", "caller_v2.py"]

caller_v2.py

@@ -0,0 +1,55 @@
+import json
+from typing import Iterator
+import gradio as gr
+from groq import Groq
+from elevenlabs.client import ElevenLabs
+import logging as log
+
+# Initialize Groq client
+client = Groq(api_key="")
+elevenlabs_client = ElevenLabs(
+    api_key=""
+)
+
+
+
+def transcribe_audio(audio_file_path, language, additional_text):
+    try:
+        bytes_data = open('greetings.mp3', 'rb').read()
+        yield "Checking ...", bytes_data
+
+    except Exception as e:
+        print(f"error: {e}")
+        log.info(f'error: {e}')
+        yield f"An error occurred: {str(e)}", None
+
+
+def speach_to_text():
+    # List of supported languages (this is an example, adjust based on Groq's actual supported languages)
+    languages = ["en", "ba", "ms", "is", "no", "id"]
+
+    # Create Gradio interface
+    iface = gr.Interface(
+        fn=transcribe_audio,
+        inputs=[
+            gr.Audio(type="filepath", label="Upload Audio File"),
+            gr.Dropdown(choices=languages, label="Select Language", value="en"),
+            # gr.Radio(["standard", "high"], label="Transcription Quality", value="standard"),
+            gr.Textbox(label="Additional Text", placeholder="Enter any additional context or instructions here...")
+        ],
+        outputs=[
+            gr.Textbox(label="Response"),
+            gr.Audio(label="Audio Stream", autoplay=True, format="mp3")
+        ],
+        title="Groq Speech-to-Text Transcription",
+        description="Upload an audio file, set parameters, and provide additional text for context in the "
+                    "transcription process."
+    )
+
+    # Launch the interface
+    iface.launch()
+
+
+# Press the green button in the gutter to run the script.
+if __name__ == '__main__':    
+    speach_to_text()

requirements.txt

@@ -0,0 +1,60 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.4.0
+certifi==2024.7.4
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+distro==1.9.0
+elevenlabs==1.7.0
+fastapi==0.112.0
+ffmpy==0.4.0
+filelock==3.15.4
+fonttools==4.53.1
+fsspec==2024.6.1
+gradio @ https://gradio-pypi-previews.s3.amazonaws.com/3dbb412d75a463affc00898b24ade9eb5116e07b/gradio-4.41.0-py3-none-any.whl#sha256=c6a08ed04050cbf8c8d17a5ee3d23af8dc2d793bef53a3a519c299f8a84f07dc
+gradio_client @ git+https://github.com/gradio-app/gradio@4bc495cb68aec014cffffce16c14ee1ddaacf7a3#subdirectory=client/python
+groq==0.9.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.24.5
+idna==3.7
+importlib_resources==6.4.0
+Jinja2==3.1.4
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+numpy==2.0.1
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+pydantic==2.8.2
+pydantic_core==2.20.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.2
+requests==2.32.3
+rich==13.7.1
+ruff==0.5.7
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+tomlkit==0.12.0
+tqdm==4.66.5
+typer==0.12.3
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+uvicorn==0.30.6
+websockets==12.0