Add audio transcription and text summarization features

README.md

@@ -8,6 +8,9 @@ sdk_version: 4.22.0
 app_file: app.py
 pinned: false
 license: mit
+models:
+openai/whisper-large-v3
+google/gemma-7b-it
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,12 +1,42 @@
 import gradio as gr
 import os
+from huggingface_hub import InferenceClient
 
 HUGGINGFACE_API_KEY = os.environ["HUGGINGFACE_API_KEY"]
 
 
-def greet(name):
-    return "Hello " + name + "!!" + HUGGINGFACE_API_KEY
+def transcript_audio(audio_file) -> str:
+    model = "openai/whisper-large-v3"
+    api = InferenceClient(model, token=HUGGINGFACE_API_KEY)
+    text = api.automatic_speech_recognition(audio_file)
+    return text
 
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+def summarize_text(text: str, bullet_points: int, conclusion: bool) -> str:
+    llm_model = "google/gemma-7b-it"
+    api = InferenceClient(llm_model, token=HUGGINGFACE_API_KEY)
+    if conclusion:
+        prompt = f"Summarize the following text into {bullet_points} bullet points and a conclusion: {text}"
+    else:
+        prompt = f"Summarize the following text into {bullet_points} bullet points: {text}"
+    summary = api.text_generation(prompt, max_new_tokens=250, do_sample=True)
+    return summary["generated_text"]
+
+def control(audio_file: gr.AudioFile, text: str, bullet_points: int, conclusion: bool) -> str:
+    if audio_file:
+        text = transcript_audio(audio_file)
+    summary = summarize_text(text, bullet_points, conclusion)
+    return summary
+# make a simeple interface, where the user can input a text and get a summary or input an audio file and get a transcript and a summary
+iface = gr.Interface(
+    fn=summarize_text,
+    inputs=[
+        gr.components.Audio(label="Audio file"),
+        gr.components.Textbox(lines=5, label="Text"),
+        gr.components.Slider(minimum=1, maximum=10, value=5, step=1, label="Number of bullet points"),
+        gr.components.Checkbox(label="Add conclusion"),
+    ],
+    outputs=gr.components.Textbox(label="Summary")
+)
+
 iface.launch()