File size: 7,409 Bytes
194ca0b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
import gradio as gr
import numpy as np
import io
from scipy.io import wavfile
import speech_recognition as sr
import soundfile as sf
# Morse code dictionary (ITU standard)
MORSE_CODE_DICT = {
'A': '.-', 'B': '-...', 'C': '-.-.', 'D': '-..', 'E': '.', 'F': '..-.',
'G': '--.', 'H': '....', 'I': '..', 'J': '.---', 'K': '-.-', 'L': '.-..',
'M': '--', 'N': '-.', 'O': '---', 'P': '.--.', 'Q': '--.-', 'R': '.-.',
'S': '...', 'T': '-', 'U': '..-', 'V': '...-', 'W': '.--', 'X': '-..-',
'Y': '-.--', 'Z': '--..', '1': '.----', '2': '..---', '3': '...--',
'4': '....-', '5': '.....', '6': '-....', '7': '--...', '8': '---..',
'9': '----.', '0': '-----', ' ': '/'
}
MORSE_TO_CHAR = {v: k for k, v in MORSE_CODE_DICT.items()}
# Morse code timing (in seconds)
DIT_DURATION = 0.1 # 100ms for dit
DAH_DURATION = 3 * DIT_DURATION # 300ms for dah
SPACE_DURATION = 7 * DIT_DURATION # 700ms for word space
CHAR_SPACE = DIT_DURATION # Space between characters
SAMPLE_RATE = 44100 # Standard audio sample rate
# Decode Morse from audio (simplified)
def decode_morse_from_audio(audio_data):
if audio_data is None:
return "", ""
sample_rate, data = audio_data
if len(data.shape) > 1:
data = data.mean(axis=1)
data = data / np.max(np.abs(data))
threshold = 0.1
signal = data > threshold
morse_code, decoded_text = "", ""
i = 0
while i < len(signal) - int(SAMPLE_RATE * DIT_DURATION):
if signal[i]:
start = i
while i < len(signal) and signal[i]:
i += 1
duration = (i - start) / sample_rate
morse_code += "-" if duration >= DAH_DURATION else "."
else:
start = i
while i < len(signal) and not signal[i]:
i += 1
pause = (i - start) / sample_rate
if pause >= SPACE_DURATION and morse_code:
decoded_text += " "
morse_code = ""
elif pause >= DIT_DURATION and morse_code:
decoded_text += MORSE_TO_CHAR.get(morse_code, "?")
morse_code = ""
i += 1
if morse_code:
decoded_text += MORSE_TO_CHAR.get(morse_code, "?")
return morse_code, decoded_text.strip()
# Convert text to Morse code
def text_to_morse(text):
text = text.upper()
morse = " ".join(MORSE_CODE_DICT.get(char, "?") for char in text if char in MORSE_CODE_DICT)
return morse
# Generate Morse code audio from text
def generate_morse_audio(morse):
audio = []
frequency = 750 # Hz for Morse tone
for symbol in morse.split():
if symbol == "/":
audio.extend([0] * int(SAMPLE_RATE * SPACE_DURATION))
else:
for char in symbol:
duration = DAH_DURATION if char == "-" else DIT_DURATION
t = np.linspace(0, duration, int(SAMPLE_RATE * duration), False)
tone = 0.5 * np.sin(2 * np.pi * frequency * t)
audio.extend(tone)
audio.extend([0] * int(SAMPLE_RATE * DIT_DURATION)) # Space between dits/dahs
audio.extend([0] * int(SAMPLE_RATE * CHAR_SPACE)) # Space between characters
audio = np.array(audio, dtype=np.float32)
buffer = io.BytesIO()
sf.write(buffer, audio, SAMPLE_RATE, format="wav")
buffer.seek(0)
return buffer
# Speech to text
def speech_to_text(audio):
recognizer = sr.Recognizer()
with sr.AudioFile(audio) as source:
audio_data = recognizer.record(source)
try:
return recognizer.recognize_google(audio_data)
except sr.UnknownValueError:
return "Could not understand audio"
except sr.RequestError:
return "Speech recognition service unavailable"
# Highlight alphabet in UI
def generate_alphabet_html(decoded_text):
html = "<div style='font-family: monospace; font-size: 16px;'>"
for char in MORSE_CODE_DICT.keys():
color = "red" if char in decoded_text.upper() else "black"
html += f"<span style='color: {color}; margin: 5px;'>{char}: {MORSE_CODE_DICT[char]}</span>"
if char in "AEIMQUZ":
html += "<br>"
html += "</div>"
return html
# Combined processing function
def process_input(text=None, speech=None, audio=None):
morse, decoded_text, audio_output = "", "", None
if text: # Text input
morse = text_to_morse(text)
decoded_text = text
audio_output = generate_morse_audio(morse)
elif speech: # Speech input
text = speech_to_text(speech)
morse = text_to_morse(text)
decoded_text = text
audio_output = generate_morse_audio(morse)
elif audio: # Live audio input
morse, decoded_text = decode_morse_from_audio(audio)
alphabet_html = generate_alphabet_html(decoded_text)
return morse, decoded_text, alphabet_html, audio_output
# Gradio UI with Blocks
with gr.Blocks(title="Morse Code Decoder & Generator") as demo:
gr.Markdown("# Morse Code Decoder & Generator")
gr.Markdown("Decode live Morse audio, or generate Morse from text/speech!")
with gr.Tab("Decode Live Audio"):
audio_input = gr.Audio(source="microphone", type="numpy", streaming=True, label="Live Audio Input")
with gr.Row():
with gr.Column():
morse_output = gr.Textbox(label="Detected Morse Code", interactive=False)
text_output = gr.Textbox(label="Decoded Text", interactive=False)
alphabet_display = gr.HTML(label="Morse Alphabet (Highlighted)")
audio_input.stream(
fn=process_input,
inputs=[audio_input],
outputs=[morse_output, text_output, alphabet_display, gr.Audio(visible=False)],
)
with gr.Tab("Generate from Text"):
text_input = gr.Textbox(label="Enter Text", placeholder="Type here...")
generate_btn = gr.Button("Generate Morse")
with gr.Row():
with gr.Column():
morse_gen_output = gr.Textbox(label="Morse Code", interactive=False)
text_gen_output = gr.Textbox(label="Original Text", interactive=False)
gen_alphabet_display = gr.HTML(label="Morse Alphabet (Highlighted)")
audio_playback = gr.Audio(label="Morse Audio Playback", interactive=False)
generate_btn.click(
fn=process_input,
inputs=[text_input],
outputs=[morse_gen_output, text_gen_output, gen_alphabet_display, audio_playback]
)
with gr.Tab("Generate from Speech"):
speech_input = gr.Audio(source="microphone", type="filepath", label="Speak Your Text")
speech_btn = gr.Button("Convert Speech to Morse")
with gr.Row():
with gr.Column():
morse_speech_output = gr.Textbox(label="Morse Code", interactive=False)
text_speech_output = gr.Textbox(label="Transcribed Text", interactive=False)
speech_alphabet_display = gr.HTML(label="Morse Alphabet (Highlighted)")
speech_audio_playback = gr.Audio(label="Morse Audio Playback", interactive=False)
speech_btn.click(
fn=process_input,
inputs=[speech_input],
outputs=[morse_speech_output, text_speech_output, speech_alphabet_display, speech_audio_playback]
)
# Launch the app
demo.launch() |