refactored for hugging face hosting

README.md

@@ -1,19 +1,30 @@
-# Hospital Copilot
+---
+title: MediScribe AI
+emoji: 🏥
+colorFrom: blue
+colorTo: indigo
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+---
+
+# MediScribe AI
 
 AI-powered medical documentation assistant for the **Gemma 4 for Good** hackathon.
 
-Listens to doctor-patient consultations and automatically generates SOAP notes, patient summaries, symptom extractions, and Twi (Akan) translations — reducing paperwork and language barriers in Ghanaian healthcare.
+Record a doctor-patient consultation via your browser mic. MediScribe transcribes it, repairs ASR errors, extracts structured clinical data, and generates a professional SOAP note and patient summary — powered by Gemma 4.
 
 ## Features
 
-- **Live transcription** via faster-whisper (runs on CPU)
-- **Symptom extraction** via Gemma 4 E2B (local, Ollama, CPU)
-- **SOAP note generation** via Gemma 4 27B (Google AI Studio)
-- **Patient summary** in plain English
-- **English ↔ Twi translation** for Ghanaian patients
-- **Patient records** stored in local SQLite
+- **Browser mic recording** — no software install needed
+- **Transcript repair + speaker labelling** via Gemma 4
+- **Structured symptom extraction** via Gemma 4 function calling
+- **RAG-grounded SOAP notes** with ICD-10 codes and WHO drug references
+- **Multimodal document analysis** — upload lab results or prescriptions
+- **Patient records** stored in SQLite
 
-## Setup
+## Setup (local)
 
 ### 1. Install dependencies
 
@@ -21,53 +32,50 @@ Listens to doctor-patient consultations and automatically generates SOAP notes,
 pip install -r requirements.txt
 ```
 
-### 2. Install Ollama and pull Gemma 4
-
-```bash
-# Install Ollama: https://ollama.com
-ollama pull gemma4:e2b
-```
-
-### 3. Configure environment
+### 2. Configure environment
 
 ```bash
 cp .env.example .env
-# Edit .env and add your Google AI Studio API key
+# Add your Google AI Studio API key
 ```
 
-Get a free API key at https://aistudio.google.com
+Get a free key at https://aistudio.google.com
 
-### 4. Run
+### 3. Run
 
 ```bash
 python app.py
 ```
 
-Open http://localhost:7860 in your browser.
+## Hugging Face Spaces
+
+Set `GEMINI_API_KEY` as a Space secret in Settings → Variables and secrets.
 
 ## Project Structure
 
 ```
-hosptial_copilot/
 ├── app.py                      # Gradio UI + app logic
 ├── agents/
-│   ├── symptom_agent.py        # Local Gemma 4 (Ollama) symptom extractor
-│   └── cloud_agents.py         # Cloud Gemma 4: SOAP, summary, translation
+│   ├── symptom_agent.py        # Symptom extractor (Gemma 4 function calling)
+│   └── cloud_agents.py         # SOAP, summary, transcript repair, document analysis
 ├── transcription/
-│   └── transcriber.py          # faster-whisper live mic transcription
+│   └── transcriber.py          # faster-whisper batch transcription
+├── rag/
+│   ├── retriever.py            # ChromaDB + sentence-transformers RAG
+│   └── data/                   # ICD-10 codes + WHO essential medicines
 ├── database/
 │   └── db.py                   # SQLite helpers
-├── requirements.txt
-└── .env.example
+└── requirements.txt
 ```
 
 ## Architecture
 
 ```
-Microphone
-  └─► faster-whisper (local, CPU)   → raw transcript
-        ├─► Gemma 4 E2B via Ollama  → symptom JSON (local CPU)
-        └─► Gemma 4 27B via API     → SOAP note + summary + Twi translation
-              └─► SQLite            → patient records
-                    └─► Gradio UI   → doctor dashboard
+Browser Mic
+  └─► faster-whisper (CPU)      → raw transcript
+        └─► Gemma 4 26B (API)   → cleaned transcript + speaker labels
+              ├─► Gemma 4 function calling → structured symptom JSON
+              ├─► ChromaDB RAG  → ICD-10 codes + drug dosages
+              └─► Gemma 4 reasoning mode → SOAP note + patient summary
+                    └─► SQLite  → patient records
 ```

agents/symptom_agent.py

@@ -1,81 +1,16 @@
-import os
-import json
-import ollama
 from agents.cloud_agents import extract_symptoms_cloud
 
-OLLAMA_MODEL = os.getenv("OLLAMA_MODEL", "gemma4:e2b")
-
-SYMPTOM_PROMPT = """You are a medical symptom extraction AI. Extract all clinical information from this transcript into valid JSON only.
-
-Return ONLY valid JSON — no markdown, no explanation, no code fences:
-{{
-  "chief_complaint": "main reason for visit",
-  "symptoms": ["list", "of", "symptoms"],
-  "duration": "how long symptoms have been present",
-  "severity": "mild | moderate | severe",
-  "associated_symptoms": ["other symptoms"],
-  "medications_mentioned": ["drugs or treatments mentioned"],
-  "allergies": ["any allergies mentioned"],
-  "vitals_mentioned": {{
-    "temperature": null,
-    "blood_pressure": null,
-    "pulse": null,
-    "weight": null
-  }},
-  "relevant_history": "past medical history",
-  "follow_up_actions": ["follow-up steps, tests, referrals"]
-}}
-
-Transcript:
-{transcript}"""
-
-
-def _extract_via_ollama(transcript: str) -> dict:
-    """Primary: local Gemma 4 E2B via Ollama."""
-    response = ollama.chat(
-        model=OLLAMA_MODEL,
-        messages=[{"role": "user", "content": SYMPTOM_PROMPT.format(transcript=transcript)}],
-        options={"temperature": 0.1},
-    )
-    raw = response["message"]["content"].strip()
-
-    # strip markdown fences if present
-    if "```" in raw:
-        parts = raw.split("```")
-        raw = parts[1] if len(parts) > 1 else parts[0]
-        if raw.startswith("json"):
-            raw = raw[4:]
-    raw = raw.strip()
-
-    result = json.loads(raw)
-    # must be a dict with at least chief_complaint to be valid
-    if not isinstance(result, dict) or "chief_complaint" not in result:
-        raise ValueError("Invalid symptom structure from Ollama")
-    return result
-
 
 def extract_symptoms(transcript: str) -> dict:
-    """
-    Extract structured symptoms from transcript.
-    Tries local Gemma 4 E2B (Ollama) first — fast, private.
-    Falls back to cloud Gemma 4 function calling on any failure — guaranteed valid schema.
-    """
+    """Extract structured symptoms via Gemma 4 function calling."""
     if not transcript.strip():
         return {}
-
-    try:
-        result = _extract_via_ollama(transcript)
-        print("[Symptoms] Extracted via local Gemma 4 E2B (Ollama)")
-        return result
-    except Exception as e:
-        print(f"[Symptoms] Ollama failed ({e}), falling back to cloud function calling...")
-
     try:
         result = extract_symptoms_cloud(transcript)
         print("[Symptoms] Extracted via cloud Gemma 4 function calling")
         return result
     except Exception as e:
-        print(f"[Symptoms] Cloud fallback also failed: {e}")
+        print(f"[Symptoms] Extraction failed: {e}")
         return {"error": str(e)}
 
 

app.py

@@ -1,4 +1,3 @@
-import threading
 from dotenv import load_dotenv
 
 load_dotenv()
@@ -19,7 +18,7 @@ from database.db import (
     get_note_for_session,
     get_symptoms_for_session,
 )
-from transcription.transcriber import LiveTranscriber
+from transcription.transcriber import transcribe_file
 from agents.symptom_agent import extract_symptoms, format_symptoms_for_display
 from agents.cloud_agents import generate_soap_note, generate_patient_summary, clean_and_label_transcript, analyze_medical_document
 from rag.retriever import (
@@ -37,12 +36,9 @@ ensure_kb()
 
 # ── State ─────────────────────────────────────────────────────────────────────
 
-_transcriber: LiveTranscriber | None = None
-_transcript_parts: list[str] = []
 _labelled_transcript: str = ""
 _document_analysis: str = ""
 _current_session_id: int | None = None
-_transcript_lock = threading.Lock()
 
 # ── Helpers ───────────────────────────────────────────────────────────────────
 
@@ -55,11 +51,6 @@ def _parse_patient_choice(choice: str) -> int:
     return int(choice.split("—")[0].strip())
 
 
-def _full_transcript() -> str:
-    with _transcript_lock:
-        return " ".join(_transcript_parts)
-
-
 def _format_icd_panel(codes: list[dict]) -> str:
     if not codes:
         return "_No ICD-10 suggestions._"
@@ -94,61 +85,27 @@ def register_patient(name, dob, gender, phone):
     return gr.update(choices=choices, value=new_val), f"Patient '{name}' registered (ID {pid})."
 
 
-def start_consultation(patient_choice, doctor_name):
-    global _transcriber, _transcript_parts, _current_session_id
+def transcribe_recording(patient_choice, doctor_name, audio_path):
+    """Called when the mic recording stops. Transcribes and cleans the audio."""
+    global _current_session_id, _labelled_transcript
 
     if not patient_choice:
-        return "No patient selected.", "", gr.update(interactive=False), gr.update(interactive=True)
+        return "No patient selected.", ""
+    if audio_path is None:
+        return "No audio recorded.", ""
 
     pid = _parse_patient_choice(patient_choice)
     _current_session_id = create_session(pid, doctor_name or "Doctor")
-
-    with _transcript_lock:
-        _transcript_parts.clear()
-    global _labelled_transcript, _document_analysis
     _labelled_transcript = ""
-    _document_analysis = ""
-
-    def on_text(text):
-        with _transcript_lock:
-            _transcript_parts.append(text)
-    _transcriber = LiveTranscriber(on_text=on_text)
-    _transcriber.start()
-
-    return (
-        "Recording... speak clearly.",
-        "",
-        gr.update(interactive=True),
-        gr.update(interactive=False),
-    )
-
-
-def poll_transcript():
-    return _full_transcript()
-
-
-def stop_consultation():
-    global _transcriber, _labelled_transcript
 
-    if _transcriber:
-        _transcriber.stop()
-        _transcriber = None
-
-    raw = _full_transcript()
+    raw = transcribe_file(audio_path)
     if not raw:
-        return "No audio captured.", "", gr.update(interactive=False), gr.update(interactive=True)
-
-    if _current_session_id:
-        update_transcript(_current_session_id, raw)
+        return "No speech detected in the recording.", ""
 
+    update_transcript(_current_session_id, raw)
     _labelled_transcript = clean_and_label_transcript(raw)
 
-    return (
-        "Consultation ended. Transcript cleaned ✓  Click 'Generate Notes' to proceed.",
-        _labelled_transcript,
-        gr.update(interactive=False),
-        gr.update(interactive=True),
-    )
+    return "Transcript ready ✓  Click 'Generate Notes' to proceed.", _labelled_transcript
 
 
 def upload_document(file):
@@ -168,20 +125,18 @@ def upload_document(file):
 
 def generate_notes():
     """RAG retrieval → cloud agents → save to DB."""
-    # Use labelled transcript if available, fall back to raw
-    transcript = _labelled_transcript or _full_transcript()
-    if not transcript:
+    if not _labelled_transcript:
         return "No transcript available.", "No transcript available.", "_No symptoms._", "_No ICD codes._", "_No drug info._", "", ""
 
-    # 1. Extract symptoms locally (Gemma 4 E2B via Ollama)
-    symptoms = extract_symptoms(transcript)
+    # 1. Extract symptoms
+    symptoms = extract_symptoms(_labelled_transcript)
     symptoms_md = format_symptoms_for_display(symptoms)
 
     # 2. RAG retrieval
     chief = symptoms.get("chief_complaint", "")
     sym_list = symptoms.get("symptoms", [])
     meds_list = symptoms.get("medications_mentioned", [])
-    rag_query = f"{chief} {' '.join(sym_list)}".strip() or transcript[:300]
+    rag_query = f"{chief} {' '.join(sym_list)}".strip() or _labelled_transcript[:300]
 
     icd_codes = retrieve_icd_codes(rag_query, n=5)
     drug_info = retrieve_drug_info(meds_list, n=3) if meds_list else []
@@ -195,12 +150,12 @@ def generate_notes():
 
     # 3. Cloud agents
     try:
-        soap = generate_soap_note(transcript, rag_context=rag_context)
+        soap = generate_soap_note(_labelled_transcript, rag_context=rag_context)
     except Exception as e:
         soap = f"_SOAP note generation failed: {e}_"
 
     try:
-        summary_en = generate_patient_summary(transcript)
+        summary_en = generate_patient_summary(_labelled_transcript)
     except Exception as e:
         summary_en = f"_Summary generation failed: {e}_"
 
@@ -261,12 +216,10 @@ body, .gradio-container { font-family: 'Segoe UI', system-ui, sans-serif; }
 #header-banner h1 { margin: 0; font-size: 1.9rem; font-weight: 700; letter-spacing: -0.5px; }
 #header-banner p  { margin: 5px 0 0; opacity: 0.85; font-size: 0.95rem; }
 
-/* Fix markdown panels — transparent so they inherit theme bg */
 .gr-markdown, .svelte-1ed2p3z, [data-testid="markdown"] {
     background: transparent !important;
 }
 
-/* Note cards — rendered SOAP/summary display */
 .note-card {
     border: 1px solid #2d4a6e;
     border-radius: 8px;
@@ -284,10 +237,8 @@ body, .gradio-container { font-family: 'Segoe UI', system-ui, sans-serif; }
 .note-card p { margin: 6px 0; }
 .note-card ul, .note-card ol { padding-left: 20px; margin: 4px 0; }
 
-/* Status bar */
 .status-bar p { font-weight: 600; color: #4a9eff; font-size: 1rem; }
 
-/* RAG accordion open panel */
 .rag-content {
     border-left: 3px solid #1a6eb5;
     padding: 10px 14px;
@@ -295,21 +246,16 @@ body, .gradio-container { font-family: 'Segoe UI', system-ui, sans-serif; }
     font-size: 0.9rem;
 }
 
-/* Tighten up accordion headers */
 .gr-accordion .label-wrap { font-weight: 600 !important; }
-
-/* Recording pulse indicator */
-@keyframes pulse { 0%,100%{opacity:1} 50%{opacity:0.4} }
-.recording p { animation: pulse 1.4s ease-in-out infinite; color: #ff4444 !important; font-weight: 700; }
 """
 
 # ── Layout ────────────────────────────────────────────────────────────────────
 
-with gr.Blocks(title="Hospital Copilot") as demo:
+with gr.Blocks(title="Hospital Copilot", css=CSS) as demo:
 
     gr.HTML("""
     <div id="header-banner">
-        <h1>🏥 Hospital Copilot</h1>
+        <h1>🏥 MediScribe AI</h1>
         <p>AI-powered medical documentation &nbsp;·&nbsp; Gemma 4 &nbsp;·&nbsp; RAG-grounded &nbsp;·&nbsp; Ghana</p>
     </div>
     """)
@@ -343,20 +289,24 @@ with gr.Blocks(title="Hospital Copilot") as demo:
 
                 # Right column — consultation
                 with gr.Column(scale=3):
-                    status_txt = gr.Markdown("_Ready. Select a patient and click Start._", elem_classes=["status-bar"])
+                    status_txt = gr.Markdown("_Ready. Select a patient, then record the consultation below._", elem_classes=["status-bar"])
 
-                    with gr.Row():
-                        start_btn = gr.Button("▶ Start Consultation", variant="primary", scale=1)
-                        stop_btn  = gr.Button("⏹ End Consultation",   variant="stop",    scale=1, interactive=False)
+                    gr.Markdown(
+                        "**Record the consultation** — click the mic to start, click stop when done. "
+                        "The transcript will appear automatically."
+                    )
+                    mic_input = gr.Audio(
+                        sources=["microphone"],
+                        type="filepath",
+                        label="Consultation Recording",
+                    )
 
                     live_transcript = gr.Textbox(
-                        label="Transcript (cleaned & speaker-labelled after consultation ends)",
+                        label="Transcript (cleaned & speaker-labelled)",
                         lines=8, max_lines=16,
                         interactive=False,
-                        placeholder="Transcript streams here as you speak. After you click End Consultation, Gemma 4 cleans and labels it automatically.",
+                        placeholder="Record the consultation above. The transcript will appear here after you stop recording.",
                     )
-                    timer = gr.Timer(value=2)
-                    timer.tick(poll_transcript, outputs=live_transcript)
 
                     with gr.Accordion("🩺 Extracted Symptoms", open=False):
                         symptoms_live = gr.Markdown("_Will populate after Generate Notes._")
@@ -380,7 +330,6 @@ with gr.Blocks(title="Hospital Copilot") as demo:
 
             generate_btn = gr.Button("⚡ Generate Notes from Transcript", variant="primary", size="lg")
 
-            # RAG panels — inside accordions so they don't show as white boxes
             with gr.Row():
                 with gr.Accordion("🏷️ ICD-10 Suggestions", open=True):
                     icd_panel = gr.Markdown("_Click Generate Notes to see suggestions._")
@@ -407,14 +356,10 @@ with gr.Blocks(title="Hospital Copilot") as demo:
                     with gr.Accordion("✏️ Edit Summary", open=False):
                         summary_edit = gr.Textbox(lines=10, interactive=True, show_label=False)
 
-            start_btn.click(
-                start_consultation,
-                inputs=[patient_dd, doctor_name],
-                outputs=[status_txt, live_transcript, stop_btn, start_btn],
-            )
-            stop_btn.click(
-                stop_consultation,
-                outputs=[status_txt, live_transcript, stop_btn, start_btn],
+            mic_input.stop_recording(
+                transcribe_recording,
+                inputs=[patient_dd, doctor_name, mic_input],
+                outputs=[status_txt, live_transcript],
             )
             generate_btn.click(
                 generate_notes,
@@ -455,17 +400,18 @@ with gr.Blocks(title="Hospital Copilot") as demo:
         # ── Tab 3: About ──────────────────────────────────────────────────
         with gr.Tab("ℹ️ About"):
             gr.Markdown("""
-## Hospital Copilot — Gemma 4 for Good
+## MediScribe AI — Gemma 4 for Good
 
 **Reducing doctor burnout. Improving care quality. Built for Ghana.**
 
 ### How it works
-1. **Live Transcription** — faster-whisper converts speech to text in real time on CPU
-2. **Symptom Extraction** — Gemma 4 E2B (local, Ollama) extracts structured clinical JSON
-3. **RAG Retrieval** — sentence-transformers + ChromaDB matches ICD-10 codes and drug dosages
-4. **SOAP Note Generation** — Gemma 4 26B (cloud) writes a grounded, accurate medical note
-5. **Patient Summary** — plain-language summary the patient can take home
-6. **Structured Records** — everything saved to local SQLite
+1. **Live Transcription** — Record the consultation via your browser mic. faster-whisper transcribes on CPU.
+2. **Transcript Repair** — Gemma 4 fixes ASR errors and labels each turn as Doctor or Patient.
+3. **Symptom Extraction** — Gemma 4 function calling extracts structured clinical JSON.
+4. **RAG Retrieval** — sentence-transformers + ChromaDB matches ICD-10 codes and drug dosages.
+5. **SOAP Note Generation** — Gemma 4 (reasoning mode) writes a grounded, accurate medical note.
+6. **Patient Summary** — plain-language summary the patient can take home.
+7. **Structured Records** — everything saved to local SQLite.
 
 ### RAG Knowledge Base
 | Collection | Entries | Source |
@@ -476,15 +422,15 @@ with gr.Blocks(title="Hospital Copilot") as demo:
 ### Technology Stack
 | Component | Model | Where |
 |---|---|---|
-| Speech-to-Text | faster-whisper (base) | Local CPU |
-| Symptom Extraction | Gemma 4 E2B (Q4_K_M) | Local CPU via Ollama |
-| Embeddings | all-MiniLM-L6-v2 | Local CPU |
+| Speech-to-Text | faster-whisper (small) | CPU |
+| Symptom Extraction | Gemma 4 26B — function calling | Google AI Studio API |
+| Embeddings | all-MiniLM-L6-v2 | CPU |
 | Vector Store | ChromaDB | Local disk |
-| SOAP / Summary | Gemma 4 26B-IT | Google AI Studio API |
+| SOAP / Summary | Gemma 4 26B-IT — reasoning mode | Google AI Studio API |
 | Storage | SQLite | Local |
-| UI | Gradio | Desktop |
+| UI | Gradio | Browser |
             """)
 
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860, share=False, css=CSS)
+    demo.launch()

requirements.txt

@@ -1,11 +1,7 @@
 gradio>=4.44.0
 faster-whisper>=1.0.0
-ollama>=0.3.0
 google-genai>=1.0.0
-sounddevice>=0.4.6
 numpy>=1.26.0
-scipy>=1.13.0
 python-dotenv>=1.0.0
-fpdf2>=2.7.9
 chromadb>=0.5.0
 sentence-transformers>=3.0.0

transcription/transcriber.py

@@ -1,16 +1,6 @@
 import os
-import queue
-import tempfile
-import threading
-import wave
-import numpy as np
-import sounddevice as sd
 from faster_whisper import WhisperModel
 
-SAMPLE_RATE = 16000
-BLOCK_SECONDS = 3
-CHANNELS = 1
-
 _model: WhisperModel | None = None
 
 
@@ -22,104 +12,13 @@ def _load_model() -> WhisperModel:
     return _model
 
 
-class LiveTranscriber:
-    """
-    Streams microphone audio, transcribes in real time, and saves the full
-    session to a WAV file for post-hoc speaker diarization.
-    """
-
-    def __init__(self, on_text):
-        self.on_text = on_text
-        self._audio_q: queue.Queue = queue.Queue()
-        self._stop_event = threading.Event()
-        self._thread: threading.Thread | None = None
-        self._stream: sd.InputStream | None = None
-
-        # accumulate all raw audio for diarization
-        self._all_audio: list[np.ndarray] = []
-        self._audio_lock = threading.Lock()
-
-        # path to saved WAV after stop()
-        self.wav_path: str | None = None
-
-    def _audio_callback(self, indata, frames, time_info, status):
-        chunk = indata.copy()
-        self._audio_q.put(chunk)
-        with self._audio_lock:
-            self._all_audio.append(chunk.flatten())
-
-    def _process_loop(self):
-        model = _load_model()
-        buffer = np.empty((0,), dtype=np.float32)
-        chunk_size = SAMPLE_RATE * BLOCK_SECONDS
-
-        while not self._stop_event.is_set():
-            try:
-                chunk = self._audio_q.get(timeout=0.5)
-                buffer = np.concatenate([buffer, chunk.flatten()])
-            except queue.Empty:
-                continue
-
-            if len(buffer) >= chunk_size:
-                audio_chunk = buffer[:chunk_size].astype(np.float32)
-                buffer = buffer[chunk_size:]
-                segments, _ = model.transcribe(
-                    audio_chunk,
-                    language="en",
-                    vad_filter=True,
-                    vad_parameters={"min_silence_duration_ms": 300},
-                )
-                text = " ".join(s.text for s in segments).strip()
-                if text:
-                    self.on_text(text)
-
-        # flush remaining audio
-        if len(buffer) > SAMPLE_RATE:
-            segments, _ = _load_model().transcribe(
-                buffer.astype(np.float32), language="en", vad_filter=True
-            )
-            text = " ".join(s.text for s in segments).strip()
-            if text:
-                self.on_text(text)
-
-    def start(self):
-        self._stop_event.clear()
-        self._all_audio.clear()
-        self._stream = sd.InputStream(
-            samplerate=SAMPLE_RATE,
-            channels=CHANNELS,
-            dtype="float32",
-            blocksize=SAMPLE_RATE,
-            callback=self._audio_callback,
-        )
-        self._stream.start()
-        self._thread = threading.Thread(target=self._process_loop, daemon=True)
-        self._thread.start()
-
-    def stop(self) -> str | None:
-        """Stop recording and save full audio to a WAV file. Returns the WAV path."""
-        self._stop_event.set()
-        if self._stream:
-            self._stream.stop()
-            self._stream.close()
-        if self._thread:
-            self._thread.join(timeout=5)
-
-        with self._audio_lock:
-            all_audio = list(self._all_audio)
-
-        if not all_audio:
-            return None
-
-        full_audio = np.concatenate(all_audio).astype(np.float32)
-        pcm = (full_audio * 32767).astype(np.int16)
-
-        tmp = tempfile.NamedTemporaryFile(suffix=".wav", delete=False)
-        with wave.open(tmp.name, "wb") as wf:
-            wf.setnchannels(CHANNELS)
-            wf.setsampwidth(2)
-            wf.setframerate(SAMPLE_RATE)
-            wf.writeframes(pcm.tobytes())
-
-        self.wav_path = tmp.name
-        return tmp.name
+def transcribe_file(file_path: str) -> str:
+    """Transcribe an audio file and return the full text."""
+    model = _load_model()
+    segments, _ = model.transcribe(
+        file_path,
+        language="en",
+        vad_filter=True,
+        vad_parameters={"min_silence_duration_ms": 300},
+    )
+    return " ".join(s.text for s in segments).strip()