Add files using upload-large-folder tool

.gitattributes

@@ -954,3 +954,17 @@ data_tts/gemini_pro_tts_sample_1546.wav filter=lfs diff=lfs merge=lfs -text
 data_tts/gemini_pro_tts_sample_155.wav filter=lfs diff=lfs merge=lfs -text
 data_tts/gcloud_tts_sample_1212.wav filter=lfs diff=lfs merge=lfs -text
 data_tts/gcloud_tts_sample_1217.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1063.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_106.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1061.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1068.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1069.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1070.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1066.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1071.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1064.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1056.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1073.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1075.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1072.wav filter=lfs diff=lfs merge=lfs -text
+data_tts/gcloud_tts_sample_1079.wav filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,414 @@
+# import sounddevice as sd
+# import streamlit as st
+# import os
+# import re
+# import numpy as np
+# import wave
+# import requests
+# from datetime import datetime
+
+# API_URL = "http://localhost:8000/transcribe"
+
+# # Record audio
+# def record_audio(duration=15, fs=16000):
+#     st.write("🔴 Recording... Speak Arabic now!")
+#     recording = sd.rec(int(duration * fs), samplerate=fs, channels=1, dtype='int16')
+#     sd.wait()
+#     st.write("✅ Recording finished")
+#     return recording, fs
+
+# # Save recording
+# def save_wav(recording, fs, out_dir="recordings"):
+#     os.makedirs(out_dir, exist_ok=True)
+#     timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+#     file_path = os.path.join(out_dir, f"recording_{timestamp}.wav")
+
+#     # Normalize
+#     max_val = np.max(np.abs(recording))
+#     if max_val > 0:
+#         recording = (recording / max_val * 32767).astype(np.int16)
+
+#     with wave.open(file_path, "wb") as wf:
+#         wf.setnchannels(1)
+#         wf.setsampwidth(2)
+#         wf.setframerate(fs)
+#         wf.writeframes(recording.tobytes())
+
+#     return file_path
+
+# # Call API
+# def transcribe_audio(file_path):
+#     with open(file_path, "rb") as f:
+#         files = {"file": (file_path, f, "audio/wav")}
+#         response = requests.post(API_URL, files=files)
+
+#     if response.status_code == 200:
+#         return response.json().get("transcription", "")
+#     else:
+#         st.error(f"❌ API Error {response.status_code}: {response.text}")
+#         return ""
+
+# # Extract phone number
+# def extract_phone_number(text):
+#     match = re.search(r"01[0-9]{9}", text)
+#     return match.group(0) if match else None
+
+# # Extract national ID
+# def extract_national_id(text):
+#     digits = re.findall(r"\d+", text)
+#     candidate = "".join(digits)
+#     if len(candidate) == 14:
+#         return candidate
+#     elif len(candidate) > 14:
+#         return candidate[:14]
+#     elif 7 <= len(candidate) < 14:
+#         return f"⚠️ Incomplete ID: {candidate} ({len(candidate)} digits)"
+#     else:
+#         return None
+
+# # ---------------- UI ----------------
+# st.title("📞 Phone & National ID Capture (with Name + Case Name)")
+
+# # Session state
+# if "phone_number" not in st.session_state:
+#     st.session_state.phone_number = None
+# if "national_id" not in st.session_state:
+#     st.session_state.national_id = None
+# if "name" not in st.session_state:
+#     st.session_state.name = ""
+# if "case_name" not in st.session_state:
+#     st.session_state.case_name = ""
+
+# # Step 1: Phone number
+# st.subheader("Step 1: Provide your phone number")
+# col1, col2 = st.columns(2)
+
+# with col1:
+#     if st.button("🎙️ Record Phone Number"):
+#         rec, fs = record_audio()
+#         wav_path = save_wav(rec, fs)
+#         st.audio(wav_path)
+#         text = transcribe_audio(wav_path)
+#         st.write("📝 Transcription:", text)
+#         phone = extract_phone_number(text)
+#         if phone:
+#             st.session_state.phone_number = phone
+#             st.success(f"📱 Detected Phone Number: {phone}")
+#         else:
+#             st.error("❌ No valid phone number detected")
+
+# with col2:
+#     phone_upload = st.file_uploader("Or upload phone number audio", type=["wav", "mp3", "m4a"])
+#     if phone_upload is not None:
+#         temp_path = os.path.join("recordings", f"upload_phone_{datetime.now().strftime('%Y%m%d_%H%M%S')}.wav")
+#         os.makedirs("recordings", exist_ok=True)
+#         with open(temp_path, "wb") as f:
+#             f.write(phone_upload.read())
+#         st.audio(temp_path)
+#         text = transcribe_audio(temp_path)
+#         st.write("📝 Transcription:", text)
+#         phone = extract_phone_number(text)
+#         if phone:
+#             st.session_state.phone_number = phone
+#             st.success(f"📱 Detected Phone Number: {phone}")
+#         else:
+#             st.error("❌ No valid phone number detected")
+
+# # Step 2: National ID
+# st.subheader("Step 2: Provide your national ID")
+# col3, col4 = st.columns(2)
+
+# with col3:
+#     if st.button("🎙️ Record National ID"):
+#         rec, fs = record_audio()
+#         wav_path = save_wav(rec, fs)
+#         st.audio(wav_path)
+#         text = transcribe_audio(wav_path)
+#         st.write("📝 Transcription:", text)
+#         nid = extract_national_id(text)
+#         if nid:
+#             st.session_state.national_id = nid
+#             st.success(f"🪪 Detected National ID: {nid}")
+#         else:
+#             st.error("❌ No valid national ID detected")
+
+# with col4:
+#     nid_upload = st.file_uploader("Or upload national ID audio", type=["wav", "mp3", "m4a"])
+#     if nid_upload is not None:
+#         temp_path = os.path.join("recordings", f"upload_nid_{datetime.now().strftime('%Y%m%d_%H%M%S')}.wav")
+#         os.makedirs("recordings", exist_ok=True)
+#         with open(temp_path, "wb") as f:
+#             f.write(nid_upload.read())
+#         st.audio(temp_path)
+#         text = transcribe_audio(temp_path)
+#         st.write("📝 Transcription:", text)
+#         nid = extract_national_id(text)
+#         if nid:
+#             st.session_state.national_id = nid
+#             st.success(f"🪪 Detected National ID: {nid}")
+#         else:
+#             st.error("❌ No valid national ID detected")
+
+# # Step 3: Manual fields
+# st.subheader("Step 3: Provide additional info")
+# st.session_state.name = st.text_input("👤 Enter your Name", st.session_state.name)
+# st.session_state.case_name = st.text_input("📂 Enter Case Name", st.session_state.case_name)
+
+# # Final summary
+# st.subheader("📋 Summary")
+# if st.session_state.phone_number:
+#     st.info(f"📱 Phone Number: {st.session_state.phone_number}")
+# if st.session_state.national_id:
+#     st.info(f"🪪 National ID: {st.session_state.national_id}")
+# if st.session_state.name:
+#     st.info(f"👤 Name: {st.session_state.name}")
+# if st.session_state.case_name:
+#     st.info(f"📂 Case Name: {st.session_state.case_name}")
+
+# if st.session_state.phone_number and st.session_state.national_id and st.session_state.name and st.session_state.case_name:
+#     st.success("✅ All details captured successfully!")
+
+
+import sounddevice as sd
+import streamlit as st
+import os
+import re
+import numpy as np
+import wave
+import requests
+from datetime import datetime
+
+API_URL = "http://localhost:8070/transcribe"
+
+# Record audio
+def record_audio(duration=15, fs=16000):
+    st.write("🔴 Recording... Speak Arabic now!")
+    # recording = sd.rec(int(duration * fs), samplerate=fs, channels=1, dtype='int16')
+    recording = sd.rec(int(16000 * 10), samplerate=16000, channels=1, dtype='int16')
+    sd.wait()
+    st.write("✅ Recording finished")
+    return recording, fs
+
+# Save recording
+# def save_wav(recording, fs, out_dir="recordings", prefix="recording"):
+#     os.makedirs(out_dir, exist_ok=True)
+#     timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+#     file_path = os.path.join(out_dir, f"{prefix}_{timestamp}.wav")
+
+#     # Normalize
+#     max_val = np.max(np.abs(recording))
+#     if max_val > 0:
+#         recording = (recording / max_val * 32767).astype(np.int16)
+
+#     with wave.open(file_path, "wb") as wf:
+#         wf.setnchannels(1)
+#         wf.setsampwidth(2)
+#         wf.setframerate(fs)
+#         wf.writeframes(recording.tobytes())
+
+#     return file_path
+import scipy.io.wavfile as wav
+
+# def save_wav(recording, fs, out_dir="recordings", prefix="recording"):
+#     os.makedirs(out_dir, exist_ok=True)
+#     timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+#     file_path = os.path.join(out_dir, f"{prefix}_{timestamp}.wav")
+
+#     # Save directly using scipy.io.wavfile
+#     wav.write(file_path, fs, recording)
+
+#     return file_path
+# Call API
+def transcribe_audio(file_path):
+    with open(file_path, "rb") as f:
+        files = {"file": (file_path, f, "audio/wav")}
+        response = requests.post(API_URL, files=files)
+
+    if response.status_code == 200:
+        return response.json().get("transcription", "")
+    else:
+        st.error(f"❌ API Error {response.status_code}: {response.text}")
+        return ""
+
+
+def save_wav(recording, fs, out_dir="recordings", prefix="recording"):
+    os.makedirs(out_dir, exist_ok=True)
+    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
+    file_path = os.path.join(out_dir, f"{prefix}_{timestamp}.wav")
+
+    # Flatten to 1D if stereo-like shape
+    if recording.ndim > 1:
+        recording = recording[:, 0]
+
+    wav.write(file_path, fs, recording.astype(np.int16))
+
+    return file_path
+
+# Extract phone number
+def extract_phone_number(text):
+    digits = re.findall(r"\d+", text)
+    candidate = "".join(digits)
+    return candidate if candidate.startswith("01") and len(candidate) == 11 else None
+
+# Extract national ID
+def extract_national_id(text):
+    digits = re.findall(r"\d+", text)
+    candidate = "".join(digits)
+    if len(candidate) == 14:
+        return candidate
+    elif len(candidate) > 14:
+        return candidate[:14]
+    elif 7 <= len(candidate) < 14:
+        return f"⚠️ Incomplete ID: {candidate} ({len(candidate)} digits)"
+    else:
+        return None
+
+# ---------------- UI ----------------
+st.title("📞 Phone, National ID, Name & Case Name Capture")
+
+# Session state
+for key in ["phone_number", "national_id", "name", "case_name"]:
+    if key not in st.session_state:
+        st.session_state[key] = None
+
+# Step 1: Phone number
+st.subheader("Step 1: Provide your phone number")
+col1, col2 = st.columns(2)
+
+with col1:
+    if st.button("🎙️ Record Phone Number"):
+        rec, fs = record_audio()
+        wav_path = save_wav(rec, fs, prefix="phone")
+        st.audio(wav_path)
+        text = transcribe_audio(wav_path)
+        st.write("📝 Transcription:", text)
+        phone = extract_phone_number(text)
+        if phone:
+            st.session_state.phone_number = phone
+            st.success(f"📱 Detected Phone Number: {phone}")
+        else:
+            st.error("❌ No valid phone number detected")
+
+with col2:
+    phone_upload = st.file_uploader("Or upload phone number audio", type=["wav", "mp3", "m4a"])
+    if phone_upload is not None:
+        temp_path = os.path.join("recordings", f"upload_phone_{datetime.now().strftime('%Y%m%d_%H%M%S')}.wav")
+        os.makedirs("recordings", exist_ok=True)
+        with open(temp_path, "wb") as f:
+            f.write(phone_upload.read())
+        st.audio(temp_path)
+        text = transcribe_audio(temp_path)
+        st.write("📝 Transcription:", text)
+        phone = extract_phone_number(text)
+        if phone:
+            st.session_state.phone_number = phone
+            st.success(f"📱 Detected Phone Number: {phone}")
+        else:
+            st.error("❌ No valid phone number detected")
+
+# Step 2: National ID
+st.subheader("Step 2: Provide your national ID")
+col3, col4 = st.columns(2)
+
+with col3:
+    if st.button("🎙️ Record National ID"):
+        rec, fs = record_audio()
+        wav_path = save_wav(rec, fs, prefix="nid")
+        st.audio(wav_path)
+        text = transcribe_audio(wav_path)
+        st.write("📝 Transcription:", text)
+        nid = extract_national_id(text)
+        if nid:
+            st.session_state.national_id = nid
+            st.success(f"🪪 Detected National ID: {nid}")
+        else:
+            st.error("❌ No valid national ID detected")
+
+with col4:
+    nid_upload = st.file_uploader("Or upload national ID audio", type=["wav", "mp3", "m4a"])
+    if nid_upload is not None:
+        temp_path = os.path.join("recordings", f"upload_nid_{datetime.now().strftime('%Y%m%d_%H%M%S')}.wav")
+        os.makedirs("recordings", exist_ok=True)
+        with open(temp_path, "wb") as f:
+            f.write(nid_upload.read())
+        st.audio(temp_path)
+        text = transcribe_audio(temp_path)
+        st.write("📝 Transcription:", text)
+        nid = extract_national_id(text)
+        if nid:
+            st.session_state.national_id = nid
+            st.success(f"🪪 Detected National ID: {nid}")
+        else:
+            st.error("❌ No valid national ID detected")
+
+# Step 3: Name (audio input)
+st.subheader("Step 3: Provide your Name")
+col5, col6 = st.columns(2)
+
+with col5:
+    if st.button("🎙️ Record Name"):
+        rec, fs = record_audio()
+        wav_path = save_wav(rec, fs, prefix="name")
+        st.audio(wav_path)
+        text = transcribe_audio(wav_path)
+        st.write("📝 Transcription:", text)
+        if text.strip():
+            st.session_state.name = text.strip()
+            st.success(f"👤 Name: {text.strip()}")
+
+with col6:
+    name_upload = st.file_uploader("Or upload name audio", type=["wav", "mp3", "m4a"])
+    if name_upload is not None:
+        temp_path = os.path.join("recordings", f"upload_name_{datetime.now().strftime('%Y%m%d_%H%M%S')}.wav")
+        os.makedirs("recordings", exist_ok=True)
+        with open(temp_path, "wb") as f:
+            f.write(name_upload.read())
+        st.audio(temp_path)
+        text = transcribe_audio(temp_path)
+        st.write("📝 Transcription:", text)
+        if text.strip():
+            st.session_state.name = text.strip()
+            st.success(f"👤 Name: {text.strip()}")
+
+# Step 4: Case Name (audio input)
+st.subheader("Step 4: Provide Case Name")
+col7, col8 = st.columns(2)
+
+with col7:
+    if st.button("🎙️ Record Case Name"):
+        rec, fs = record_audio()
+        wav_path = save_wav(rec, fs, prefix="case_name")
+        st.audio(wav_path)
+        text = transcribe_audio(wav_path)
+        st.write("📝 Transcription:", text)
+        if text.strip():
+            st.session_state.case_name = text.strip()
+            st.success(f"📂 Case Name: {text.strip()}")
+
+with col8:
+    case_upload = st.file_uploader("Or upload case name audio", type=["wav", "mp3", "m4a"])
+    if case_upload is not None:
+        temp_path = os.path.join("recordings", f"upload_case_{datetime.now().strftime('%Y%m%d_%H%M%S')}.wav")
+        os.makedirs("recordings", exist_ok=True)
+        with open(temp_path, "wb") as f:
+            f.write(case_upload.read())
+        st.audio(temp_path)
+        text = transcribe_audio(temp_path)
+        st.write("📝 Transcription:", text)
+        if text.strip():
+            st.session_state.case_name = text.strip()
+            st.success(f"📂 Case Name: {text.strip()}")
+
+# Final summary
+st.subheader("📋 Summary")
+if st.session_state.phone_number:
+    st.info(f"📱 Phone Number: {st.session_state.phone_number}")
+if st.session_state.national_id:
+    st.info(f"🪪 National ID: {st.session_state.national_id}")
+if st.session_state.name:
+    st.info(f"👤 Name: {st.session_state.name}")
+if st.session_state.case_name:
+    st.info(f"📂 Case Name: {st.session_state.case_name}")
+
+if st.session_state.phone_number and st.session_state.national_id and st.session_state.name and st.session_state.case_name:
+    st.success("✅ All details captured successfully!")

data_tts/gcloud_tts_sample_1056.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9333b44bb49675dff79edb354241435ed24507dfc635e53092388905416b7e4c
+size 169024

data_tts/gcloud_tts_sample_106.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43445c70dd5c0d5044e572a74bc69dffc339945b99af9efe5031276a747ef909
+size 130108

data_tts/gcloud_tts_sample_1061.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3524af71bf64a5b8a59f4de4bdff13420f6194b6b453b14e7ee49789dfbb95c2
+size 147324

data_tts/gcloud_tts_sample_1063.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052cff5f5a08273ac351ffadc3da7c2d6e1f409ce70d1a1a394206b8e1fae99a
+size 161550

data_tts/gcloud_tts_sample_1064.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82cc4726b248be1cbd47af2df3cab02d0d8f2dca917affda2ac2d50f49f6827d
+size 130260

data_tts/gcloud_tts_sample_1066.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5526c0adabc6a79521fe45f4ad2add8311fd2808ba1f1ea119ec8cfc7c8fbed6
+size 168918

data_tts/gcloud_tts_sample_1068.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43068a068ddf96a420413ee1ec2ad26dfacc337a9da1f80f3b8bbaedd0c00cf
+size 139066

data_tts/gcloud_tts_sample_1069.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8028cc6732c60b03851aa21d07d4c13022e27ab88541eca9019cf6209f47e564
+size 119588

data_tts/gcloud_tts_sample_1070.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9017d2c8c9737a2dc4819a10019a81b588bb59296f38e42821628fb97e146d95
+size 153662

data_tts/gcloud_tts_sample_1071.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f2eccbad15023901450e5bb7a4ca33a067376f08748110ee66485d513103c0
+size 135812

data_tts/gcloud_tts_sample_1072.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135a90200801bc5ee7fcd24a13d5bc649c503193a4fd8937726d0f19e8ffe57d
+size 169292

data_tts/gcloud_tts_sample_1073.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ea22ae2e484ee740bec3e6a7a0e31d41c5518e6a0ad0b5f462f42874c5d053a
+size 152684

data_tts/gcloud_tts_sample_1075.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234d47f5344f3543812e8322a6fcc485726c7108084c8cf84988dbae6ea3b65e
+size 153386

data_tts/gcloud_tts_sample_1079.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4079db5596b969843598eeeb223510241812614f92464fd91913d1289dca7336
+size 178802