Hugging Face's logo

Spaces:
JPLTedCas
/
ASRinServer
Sleeping

App Files Community
JPLTedCas commited on
Commit
abc40d6
•
1 Parent(s): 1ee847b

Upload 3 files

Browse files
Files changed (3) hide show
  1. main.py +133 -0
  2. templates/Index.html +27 -0
  3. templates/Index_old.html +0 -0
main.py ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from flask import Flask, render_template
2
+ from flask_socketio import SocketIO
3
+ import speech_recognition as sr
4
+
5
+ app = Flask(__name__)
6
+ socketio = SocketIO(app)
7
+
8
+ @app.route('/')
9
+ def index():
10
+ return render_template('index.html')
11
+
12
+ @socketio.on('message')
13
+ def handle_message(message):
14
+ print(f'Received: {message}')
15
+ socketio.emit('response', message)
16
+
17
+ @socketio.on('recognize_speech')
18
+ def recognize_speech():
19
+ r = sr.Recognizer()
20
+ with sr.Microphone() as source:
21
+ print("Escuchando...")
22
+ audio = r.listen(source)
23
+ try:
24
+ recognized_text = r.recognize_google(audio, language='es-ES')
25
+ print(f"Texto reconocido: {recognized_text}")
26
+ socketio.emit('response', recognized_text)
27
+ except sr.UnknownValueError:
28
+ print("No se pudo reconocer el audio")
29
+ except sr.RequestError as e:
30
+ print(f"Error en la solicitud a Google: {e}")
31
+
32
+ if __name__ == '__main__':
33
+ socketio.run(app)
34
+
35
+
36
+
37
+
38
+
39
+
40
+
41
+
42
+
43
+
44
+
45
+
46
+
47
+
48
+
49
+
50
+
51
+
52
+
53
+ #from flask import Flask, render_template
54
+ ##from deepgram import Deepgram
55
+ #from dotenv import load_dotenv
56
+ #import os
57
+ #import asyncio
58
+ #from aiohttp import web
59
+ #from aiohttp_wsgi import WSGIHandler
60
+
61
+ #from typing import Dict, Callable
62
+
63
+
64
+ #load_dotenv()
65
+
66
+ #app = Flask('aioflask')
67
+
68
+ ##dg_client = Deepgram(os.getenv('DEEPGRAM_API_KEY'))
69
+
70
+ #async def process_audio(fast_socket: web.WebSocketResponse):
71
+ # async def get_transcript(data: Dict) -> None:
72
+ # if 'channel' in data:
73
+ # transcript = data['channel']['alternatives'][0]['transcript']
74
+
75
+ # if transcript:
76
+ # await fast_socket.send_str(transcript)
77
+
78
+ # deepgram_socket = await connect_to_deepgram(get_transcript)
79
+ # #########################################
80
+ # #r = sr.Recognizer()
81
+ # #with sr.Microphone() as source:
82
+ # # print("Listening...")
83
+ # # r.pause_threshold = 1
84
+ # # audio = r.adjust_for_ambient_noise(source)
85
+ # # audio = r.listen(source)
86
+ # #try:
87
+ # # print("Recognizing...")
88
+ # # query = r.recognize_google(get_transcript, language='es-ES')
89
+ # # print(f"User said: {query}\n")
90
+ # #except Exception as e:
91
+ # # print(e)
92
+ # # print("Unable to Recognize your voice.")
93
+ # # return "none"
94
+
95
+
96
+
97
+
98
+ # ########################################
99
+ # return deepgram_socket
100
+
101
+ #async def connect_to_deepgram(transcript_received_handler: Callable[[Dict], None]) -> str:
102
+ # try:
103
+ # socket = await dg_client.transcription.live({'punctuate': True, 'interim_results': False})
104
+ # socket.registerHandler(socket.event.CLOSE, lambda c: print(f'Connection closed with code {c}.'))
105
+ # socket.registerHandler(socket.event.TRANSCRIPT_RECEIVED, transcript_received_handler)
106
+
107
+ # return socket
108
+ # except Exception as e:
109
+ # raise Exception(f'Could not open socket: {e}')
110
+
111
+ #@app.route('/')
112
+ #def index():
113
+ # return render_template('index.html')
114
+
115
+ #async def socket(request):
116
+ # ws = web.WebSocketResponse()
117
+ # await ws.prepare(request)
118
+
119
+ # deepgram_socket = await process_audio(ws)
120
+
121
+ # while True:
122
+ # data = await ws.receive_bytes()
123
+ # deepgram_socket.send(data)
124
+
125
+
126
+
127
+ #if __name__ == "__main__":
128
+ # loop = asyncio.get_event_loop()
129
+ # aio_app = web.Application()
130
+ # wsgi = WSGIHandler(app)
131
+ # aio_app.router.add_route('*', '/{path_info: *}', wsgi.handle_request)
132
+ # aio_app.router.add_route('GET', '/listen', socket)
133
+ # web.run_app(aio_app, port=5555)
templates/Index.html ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!DOCTYPE html>
2
+ <html>
3
+ <head>
4
+ <title>WebSockets y Reconocimiento de Voz</title>
5
+ </head>
6
+ <body>
7
+ <div id="output"></div>
8
+ <button onclick="startRecognition()">Comenzar Reconocimiento</button>
9
+ <script src="https://cdnjs.cloudflare.com/ajax/libs/socket.io/4.0.1/socket.io.js"></script>
10
+ <script>
11
+ const socket = io.connect('http://' + document.domain + ':' + location.port);
12
+
13
+ socket.on('response', function (message) {
14
+ const output = document.getElementById('output');
15
+ output.innerHTML = message;
16
+ });
17
+
18
+ function startRecognition() {
19
+ socket.emit('recognize_speech');
20
+ }
21
+ </script>
22
+ </body>
23
+ </html>
24
+
25
+
26
+
27
+
templates/Index_old.html ADDED
File without changes