Duplicate from Hunzla/whisperaudio

.gitattributes

@@ -0,0 +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

README.md

@@ -0,0 +1,14 @@
+---
+title: Whisperaudio
+emoji: 🚀
+colorFrom: green
+colorTo: red
+sdk: gradio
+sdk_version: 3.39.0
+app_file: app.py
+pinned: false
+license: openrail
+duplicated_from: Hunzla/whisperaudio
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,106 @@
+from transformers import pipeline
+asr_pipe = pipeline("automatic-speech-recognition", model="Abdullah17/whisper-small-urdu")
+from difflib import SequenceMatcher
+import json
+import socket
+
+def get_local_ip():
+    try:
+        # Create a socket connection to a remote host (here, google.com)
+        s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+        s.connect(("8.8.8.8", 80))
+        local_ip = s.getsockname()[0]
+        s.close()
+        return local_ip
+    except Exception as e:
+        print(f"Error getting local IP: {e}")
+        return None
+
+
+
+with open("tasks.json", "r",encoding="utf-8") as json_file:
+    urdu_data = json.load(json_file)
+# List of commands
+# commands = [
+#     "نمائندے ایجنٹ نمائندہ",
+#     "  سم  ایکٹیویٹ ",
+#     " سم  بلاک بند ",
+#     "موبائل پیکیجز انٹرنیٹ پیکیج",
+#     " چالان جمع چلان",
+#     " گانا "
+# ]
+# replies = [
+# 1,2,
+# ]
+# Function to find the most similar command
+def find_most_similar_command(statement, command_list):
+    best_match = None
+    highest_similarity = 0
+    i=0
+    for sub_list in command_list:
+     for command in sub_list:
+        similarity = SequenceMatcher(None, statement, command).ratio()
+        print(i,"similarity",similarity)
+        if similarity > highest_similarity:
+            highest_similarity = similarity
+            best_match = command
+            reply=i
+     i+=1
+
+    return best_match,reply
+
+transcript_only=["1","3","4"]
+col_names={'1':"name",'3':"address",'4':"order"}
+def send_data_to_db(menu_id,col_value,order_id):
+    import requests
+    col_name=col_names[menu_id]
+    # API endpoint URL
+    url = 'https://pizzahut.softinfix.tech/api/save_order?'+col_name+'='+col_value+"&order_id"+"="+order_id
+    payload = {}
+    headers = {}
+
+    response = requests.request("GET", url, headers=headers, data=payload)
+
+    # Print response
+    print(response.status_code)
+    print(response.text)
+
+def transcribe_the_command(audio,menu_id,order_id):
+      local_ip = get_local_ip()
+      if local_ip:
+         print(f"Local IP Address: {local_ip}")
+      else:
+         print("Local IP could not be determined.")
+      import soundfile as sf
+      sample_rate, audio_data = audio
+      file_name = "recorded_audio.wav"
+      sf.write(file_name, audio_data, sample_rate)
+    # Convert stereo to mono by averaging the two channels
+      print(menu_id)
+
+      transcript = asr_pipe(file_name)["text"]
+      if menu_id in transcript_only:
+        col_value=transcript
+        send_data_to_db(menu_id,col_value,order_id)
+        print("data uploaded successfully!")
+      else:
+        commands=urdu_data[menu_id]
+        print(commands)
+        most_similar_command,reply = find_most_similar_command(transcript, commands)
+        print(f"Given Statement: {transcript}")
+        print(f"Most Similar Command: {most_similar_command}\n")
+        print(reply)
+        return reply
+# get_text_from_voice("urdu.wav")
+import gradio as gr
+
+
+iface = gr.Interface(
+    fn=transcribe_the_command,
+    inputs=[gr.inputs.Audio(label="Recorded Audio",source="microphone"),gr.inputs.Textbox(label="menu_id"),gr.inputs.Textbox(label="order_id")],
+    outputs="text",
+    title="Whisper Small Urdu Command",
+    description="Realtime demo for Urdu speech recognition using a fine-tuned Whisper small model and outputting the estimated command on the basis of speech transcript.",
+)
+
+iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers[torch]
+soundfile

tasks.json

@@ -0,0 +1,17 @@
+{
+  "0": [
+    ["کیا آپ میری مدد کر سکتے ہیں","مجھے نمائندے سے بات کرنی ہے","مجھے مدد کی ضرورت ہے","مجھے ایجنٹ سے بات کرنی ہے۔"],
+    ["آرڈر کریں ","آرڈر پلیس کر دیں","رکھیں آرڈر","میں نے آرڈر کرنا ہے۔","مجھے آرڈر کرنا ہے"],
+   [ "آرڈر کا اسٹیٹس پتا کرنا ہے","آرڈر کی حالت پتا کرنی ہے","آرڈر کی کنڈیشن کیا ہے","اوڈر کی تفیلات جانتی ہے","میں نے آرڈر کیا تھا"]
+  ],
+  "2": [
+ [ "لاہور","لہور","لاهور", "لہوڑ", "لاھور"],
+    [ "کراچی", "کرچی", "کراچ","کرچ","کرچے"],
+    [   "اسلام آباد", "اسلم آباد","اسلماباد","اسلامباد","اسلمباد","اسلامآبد"]
+  ],
+  "3": [
+    "تیسرا بیان اندراج ۱",
+    "تیسرا بیان اندراج ۲",
+    "تیسرا بیان اندراج ۳"
+  ]
+}