Spaces:
Build error
Build error
Update requirements.txt
Browse files- requirements.txt +12 -139
requirements.txt
CHANGED
|
@@ -1,139 +1,12 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
def play_start_sound():
|
| 15 |
-
try:
|
| 16 |
-
play(start_beep)
|
| 17 |
-
except:
|
| 18 |
-
pass
|
| 19 |
-
|
| 20 |
-
def play_end_sound():
|
| 21 |
-
try:
|
| 22 |
-
play(end_beep)
|
| 23 |
-
except:
|
| 24 |
-
pass
|
| 25 |
-
|
| 26 |
-
def start_recording(audio_time_limit):
|
| 27 |
-
global is_recording
|
| 28 |
-
is_recording = True
|
| 29 |
-
recognizer = sr.Recognizer()
|
| 30 |
-
microphone = sr.Microphone()
|
| 31 |
-
|
| 32 |
-
play_start_sound()
|
| 33 |
-
|
| 34 |
-
with microphone as source:
|
| 35 |
-
recognizer.adjust_for_ambient_noise(source, duration=0.5)
|
| 36 |
-
try:
|
| 37 |
-
audio = recognizer.listen(source, timeout=3, phrase_time_limit=audio_time_limit)
|
| 38 |
-
text = recognizer.recognize_google(audio)
|
| 39 |
-
return text
|
| 40 |
-
except sr.WaitTimeoutError:
|
| 41 |
-
return ""
|
| 42 |
-
except sr.UnknownValueError:
|
| 43 |
-
return ""
|
| 44 |
-
except Exception as e:
|
| 45 |
-
print(f"Error: {str(e)}")
|
| 46 |
-
return ""
|
| 47 |
-
finally:
|
| 48 |
-
play_end_sound()
|
| 49 |
-
is_recording = False
|
| 50 |
-
|
| 51 |
-
def transcribe_audio(audio_time_limit=10):
|
| 52 |
-
def execute_recording():
|
| 53 |
-
nonlocal result
|
| 54 |
-
result = start_recording(audio_time_limit)
|
| 55 |
-
|
| 56 |
-
result = ""
|
| 57 |
-
recording_thread = threading.Thread(target=execute_recording)
|
| 58 |
-
recording_thread.start()
|
| 59 |
-
|
| 60 |
-
start_time = time()
|
| 61 |
-
while is_recording and (time() - start_time) < audio_time_limit:
|
| 62 |
-
time_elapsed = time() - start_time
|
| 63 |
-
time_left = max(0, audio_time_limit - time_elapsed)
|
| 64 |
-
progress = 1 - (time_left / audio_time_limit)
|
| 65 |
-
yield {"__type__": "update", "value": f"🎤 Recording... {time_left:.1f}s left", "visible": True}, {"__type__": "update", "value": "", "visible": True}
|
| 66 |
-
gr.sleep(0.1)
|
| 67 |
-
|
| 68 |
-
recording_thread.join()
|
| 69 |
-
yield {"__type__": "update", "value": "✅ Done!", "visible": True}, {"__type__": "update", "value": result, "visible": True}
|
| 70 |
-
|
| 71 |
-
def create_ui():
|
| 72 |
-
css = """
|
| 73 |
-
.mic-button {
|
| 74 |
-
background: linear-gradient(45deg, #FF3366, #BA265D) !important;
|
| 75 |
-
border: none !important;
|
| 76 |
-
color: white !important;
|
| 77 |
-
padding: 12px !important;
|
| 78 |
-
border-radius: 50% !important;
|
| 79 |
-
height: 50px !important;
|
| 80 |
-
width: 50px !important;
|
| 81 |
-
margin-left: 10px !important;
|
| 82 |
-
}
|
| 83 |
-
.mic-button:hover {
|
| 84 |
-
transform: scale(1.05) !important;
|
| 85 |
-
}
|
| 86 |
-
.input-with-mic {
|
| 87 |
-
display: flex !important;
|
| 88 |
-
align-items: center !important;
|
| 89 |
-
gap: 10px !important;
|
| 90 |
-
}
|
| 91 |
-
.status-message {
|
| 92 |
-
font-style: italic;
|
| 93 |
-
color: #666;
|
| 94 |
-
margin-top: 5px;
|
| 95 |
-
}
|
| 96 |
-
"""
|
| 97 |
-
|
| 98 |
-
with gr.Blocks(css=css) as demo:
|
| 99 |
-
gr.Markdown("## 🎤 Speech to Text Converter")
|
| 100 |
-
|
| 101 |
-
with gr.Group():
|
| 102 |
-
with gr.Row():
|
| 103 |
-
text_input = gr.Textbox(
|
| 104 |
-
label="Your Input",
|
| 105 |
-
placeholder="Click the mic button and speak...",
|
| 106 |
-
elem_classes=["input-box"],
|
| 107 |
-
scale=9
|
| 108 |
-
)
|
| 109 |
-
mic_button = gr.Button(
|
| 110 |
-
"🎤",
|
| 111 |
-
elem_classes=["mic-button"],
|
| 112 |
-
scale=1
|
| 113 |
-
)
|
| 114 |
-
|
| 115 |
-
status_display = gr.Textbox(
|
| 116 |
-
label="Status",
|
| 117 |
-
visible=False,
|
| 118 |
-
interactive=False,
|
| 119 |
-
elem_classes=["status-message"]
|
| 120 |
-
)
|
| 121 |
-
|
| 122 |
-
mic_button.click(
|
| 123 |
-
fn=transcribe_audio,
|
| 124 |
-
inputs=[gr.Slider(5, 30, value=10, label="Recording time limit (seconds)")],
|
| 125 |
-
outputs=[status_display, text_input],
|
| 126 |
-
show_progress="hidden"
|
| 127 |
-
)
|
| 128 |
-
|
| 129 |
-
gr.Examples(
|
| 130 |
-
examples=["Hello world", "How are you today?", "Please convert my speech to text"],
|
| 131 |
-
inputs=text_input,
|
| 132 |
-
label="Try these examples:"
|
| 133 |
-
)
|
| 134 |
-
|
| 135 |
-
return demo
|
| 136 |
-
|
| 137 |
-
if __name__ == "__main__":
|
| 138 |
-
demo = create_ui()
|
| 139 |
-
demo.launch(debug=True)
|
|
|
|
| 1 |
+
streamlit==1.28.0
|
| 2 |
+
requests>=2.31.0
|
| 3 |
+
transformers
|
| 4 |
+
transformers>=4.25.0
|
| 5 |
+
torch>=1.10.0
|
| 6 |
+
accelerate>=0.18.0
|
| 7 |
+
huggingface_hub==0.25.2
|
| 8 |
+
python-dotenv>=1.0.0
|
| 9 |
+
|
| 10 |
+
numpy>=1.24.0
|
| 11 |
+
audio-recorder-streamlit
|
| 12 |
+
torchaudio>=2.0.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|