Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

.gitignore

@@ -0,0 +1,4 @@
+.venv/
+__pycache__/
+*.pyc
+.env

README.md

@@ -1,14 +1,14 @@
----
-title: Audiotranscribe
-emoji: 🏢
-colorFrom: red
-colorTo: purple
-sdk: gradio
-sdk_version: 6.12.0
-app_file: app.py
-pinned: false
-license: apache-2.0
-short_description: Transcribe Audio and Create a Summary
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Audiotranscribe
+emoji: 🏢
+colorFrom: red
+colorTo: purple
+sdk: gradio
+sdk_version: 6.12.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+short_description: Transcribe Audio and Create a Summary
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,51 +1,126 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-client = InferenceClient()
-
-
-def transcribe(audio):
-    if audio is None:
-        return "", ""
-    text = client.automatic_speech_recognition(audio, model="openai/whisper-base")
-    return text.text, ""
-
-
-def summarize(text):
-    if not text or not text.strip():
-        return "No text to summarize."
-    if len(text.split()) < 30:
-        return "Text is too short to summarize."
-    result = client.summarization(text, model="facebook/bart-large-cnn")
-    return result.summary_text
-
-
-with gr.Blocks(title="Audio Transcription & Summary") as demo:
-    gr.Markdown("# 🎙️ Audio Transcription & Summary")
-    gr.Markdown("Upload or record audio to transcribe it, then generate a summary.")
-
-    with gr.Row():
-        audio_input = gr.Audio(type="filepath", label="Upload or Record Audio")
-
-    with gr.Row():
-        transcribe_btn = gr.Button("Transcribe", variant="primary")
-
-    transcription_output = gr.Textbox(label="Transcription", lines=10)
-
-    with gr.Row():
-        summarize_btn = gr.Button("Summarize", variant="secondary")
-
-    summary_output = gr.Textbox(label="Summary", lines=5)
-
-    transcribe_btn.click(
-        fn=transcribe,
-        inputs=audio_input,
-        outputs=[transcription_output, summary_output],
-    )
-    summarize_btn.click(
-        fn=summarize,
-        inputs=transcription_output,
-        outputs=summary_output,
-    )
-
-demo.launch()
+import os
+import re
+import tempfile
+
+import gradio as gr
+from dotenv import load_dotenv
+from huggingface_hub import InferenceClient
+
+load_dotenv()
+
+asr_client = InferenceClient(provider="hf-inference")
+llm_client = InferenceClient()
+
+LLM_MODEL = "meta-llama/Llama-3.3-70B-Instruct"
+
+
+def transcribe_and_summarize(audio):
+    if audio is None:
+        return "", "", ""
+    try:
+        text = asr_client.automatic_speech_recognition(audio, model="openai/whisper-large-v3-turbo")
+        transcript = text.text
+    except Exception as e:
+        return "", f"Transcription failed: {e}", ""
+    if len(transcript.split()) < 30:
+        return transcript, "Text is too short to summarize.", ""
+    try:
+        result = llm_client.chat_completion(
+            model=LLM_MODEL,
+            messages=[
+                {"role": "system", "content": "You are a helpful assistant. Summarize the following text concisely."},
+                {"role": "user", "content": transcript},
+            ],
+            max_tokens=256,
+        )
+        return transcript, result.choices[0].message.content, ""
+    except Exception as e:
+        return transcript, f"Summarization failed: {e}", ""
+
+
+def extract_action_items(text):
+    if not text or not text.strip():
+        return "No text to extract action items from."
+    try:
+        result = llm_client.chat_completion(
+            model=LLM_MODEL,
+            messages=[
+                {"role": "system", "content": (
+                    "You are a helpful assistant. Extract all action items from the following text. "
+                    "For each action item, identify the owner (if mentioned) and any deadline. "
+                    "Format as a numbered list: '1. [Owner] - Action item (Deadline: ...)'. "
+                    "If no action items are found, say 'No action items found.'"
+                )},
+                {"role": "user", "content": text},
+            ],
+            max_tokens=512,
+        )
+        return result.choices[0].message.content
+    except Exception as e:
+        return f"Action item extraction failed: {e}"
+
+
+def _generate_filename(summary):
+    if summary and summary.strip() and not summary.startswith(("No text", "Text is too short", "Summarization failed")):
+        slug = re.sub(r"[^a-zA-Z0-9 ]", "", summary[:60]).strip()
+        slug = re.sub(r"\s+", "_", slug).lower()
+        if slug:
+            return f"{slug}.txt"
+    return "transcript_output.txt"
+
+
+def download_txt(transcript, summary, action_items):
+    parts = []
+    if transcript and transcript.strip():
+        parts.append("=== TRANSCRIPTION ===\n" + transcript)
+    if summary and summary.strip():
+        parts.append("=== SUMMARY ===\n" + summary)
+    if action_items and action_items.strip():
+        parts.append("=== ACTION ITEMS ===\n" + action_items)
+    if not parts:
+        return None
+    content = "\n\n".join(parts)
+    filename = _generate_filename(summary)
+    path = os.path.join(tempfile.gettempdir(), filename)
+    with open(path, "w", encoding="utf-8") as f:
+        f.write(content)
+    return path
+
+
+with gr.Blocks(title="Audio Transcription & Summary") as demo:
+    gr.Markdown("# 🎙️ Audio Transcription & Summary")
+    gr.Markdown("Upload an audio file or record from your microphone, then transcribe, summarize, and extract action items.")
+
+    with gr.Row():
+        audio_input = gr.Audio(sources=["upload", "microphone"], type="filepath", label="Upload or Record Audio")
+
+    transcribe_summarize_btn = gr.Button("Transcribe & Summarize", variant="primary")
+
+    transcription_output = gr.Textbox(label="Transcription", lines=10)
+    summary_output = gr.Textbox(label="Summary", lines=5)
+
+    with gr.Row():
+        action_btn = gr.Button("Extract Action Items", variant="secondary")
+
+    action_output = gr.Textbox(label="Action Items", lines=5)
+
+    download_file = gr.File(label="Download", interactive=False)
+    download_btn = gr.Button("Download as .txt")
+
+    transcribe_summarize_btn.click(
+        fn=transcribe_and_summarize,
+        inputs=audio_input,
+        outputs=[transcription_output, summary_output, action_output],
+    )
+    action_btn.click(
+        fn=extract_action_items,
+        inputs=transcription_output,
+        outputs=action_output,
+    )
+    download_btn.click(
+        fn=download_txt,
+        inputs=[transcription_output, summary_output, action_output],
+        outputs=download_file,
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio>=4.0.0
+huggingface_hub>=0.20.0
+python-dotenv>=1.0.0