Hugging Face's logo

Spaces:
Salman11223
/
audio_translation
Sleeping

App Files Community
audio_translation
File size: 14,314 Bytes 
ed2fbbc
 
 
 
 
 
 
84d1f79
ed2fbbc
084c4e2
ed2fbbc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34f4ff9
 
ed2fbbc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34f4ff9
ed2fbbc
 
 
 
 
 
 
 
 
 
 
 
 
 
34f4ff9
ed2fbbc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34f4ff9
 
 
ed2fbbc
 
 
 
 
34f4ff9
 
 
 
 
 
 
 
 
 
 
 
 
 
084c4e2
 
 
 
34f4ff9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ed2fbbc
 
 
34f4ff9
 
 
 
 
 
 
 
 
 
 
ed2fbbc
34f4ff9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf0d89b
34f4ff9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
 
import os
import moviepy.editor as mp
import assemblyai as aai
import requests
import azure.cognitiveservices.speech as speechsdk
from moviepy.editor import AudioFileClip
from gradio_client import Client

class Translate:
    def __init__(self, video_path,original_language, target_language):
        self.video_path = video_path
        self.target_language = target_language
        self.original_language=original_language
        self.aai_api_key = "c29eb650444a4ae4be6a787ebb15d5e2"
        self.translation_api_key = "394833878dd54214886cd81a35ac35dc"
        self.spechtotxt_key = "07ac642da789462d87ad47a790ec6d5f"

    def extract_audio(self):
        aai.settings.api_key = self.aai_api_key
        video = mp.VideoFileClip(self.video_path)
        audio = video.audio
        audio_path = "audio.wav"
        audio.write_audiofile(audio_path)
        print("Audio extracted successfully!")
        return audio_path


    def org_language_parameters(self,original_language):
        if original_language == 'English':
            self.lan_code='en'
        elif original_language =='German':
            self.lan_code='de'
        elif original_language =='French':
            self.lan_code='fr'
        elif original_language =='Spanish':
            self.lan_code='es'
        else:
            self.lan_code = ''


    def set_language_parameters(self, target_language):
            if target_language == 'English':
                self.language_code = 'en-US'
                self.trans_code = 'en'
            elif target_language == 'German':
                self.language_code = 'de-DE'
                self.trans_code = 'de'
            elif target_language == 'French':
                self.language_code = 'fr-CA'
                self.trans_code = 'fr'
            elif target_language == 'Spanish':
                self.language_code = 'es-ES'
                self.trans_code = 'es'
            elif target_language == 'Urdu':
                self.language_code = 'ur-PK'
                self.trans_code = 'ur'
            else:
                # Handle unsupported languages or set default values
                self.voice_names = []
                self.language_code = ''
                self.trans_code = ''


            print("Target Language:", target_language)
            print("Trans Code:", self.trans_code)

    def get_voice_names(self):
        return self.voice_names

    def get_language_code(self):
        return self.language_code





    def transcribe_audio(self, audio_path):
        aai.settings.api_key = self.aai_api_key
        config = aai.TranscriptionConfig(self.lan_code)
        transcriber = aai.Transcriber(config=config)
        transcript = transcriber.transcribe(audio_path)
        file_path = "transcript.srt"
        filepath = "t.txt"
        with open(file_path, "w") as file:
            file.write(transcript.export_subtitles_srt())
        with open(filepath, "w") as file:
            file.write(transcript.text)




    def translate_text(self, text):
        base_url = "https://api.cognitive.microsofttranslator.com"
        endpoint = "/translate"
        headers = {
            "Ocp-Apim-Subscription-Key": self.translation_api_key,
            "Content-Type": "application/json",
            "Ocp-Apim-Subscription-Region": "southeastasia"
        }

        params = {
            "api-version": "3.0",
            "to": self.trans_code
        }
        body = [{"text": text}]

        response = requests.post(base_url + endpoint, headers=headers, params=params, json=body)
        response.raise_for_status()
        translation = response.json()[0]["translations"][0]["text"]
        return translation




    def transcribe_and_translate(self):
        audio_path = self.extract_audio()
        self.org_language_parameters(self.original_language)
        self.transcribe_audio(audio_path)

        self.set_language_parameters(self.target_language)
        # Assuming t.txt contains the original text
        with open("t.txt", 'r', encoding='utf-8') as text_file:
            original_text = text_file.read()
        self.org_language_parameters(self.original_language)
        # Translate the entire original text
        translated_text = self.translate_text(original_text)

        # Write the translated text to a new text file
        translated_text_path = "translated_text.txt"
        with open(translated_text_path, 'w', encoding='utf-8') as translated_file:
            translated_file.write(translated_text)

        print("Translation complete. Translated text saved to:", translated_text_path)
        return translated_text_path































# class Translate:
#     def __init__(self, video_path, target_language,original_language,speaking_rate):
#         self.video_path = video_path
#         self.target_language = target_language
#         self.original_language=original_language
#         self.aai_api_key = "c29eb650444a4ae4be6a787ebb15d5e2"
#         self.txtospech_key = "358c77527e48454cbf5bf2bd54f03161"
#         self.translation_api_key = "394833878dd54214886cd81a35ac35dc"
#         self.spechtotxt_key = "07ac642da789462d87ad47a790ec6d5f"
#         self.speaking_rate= speaking_rate
#         self.print_parameters()

#     def print_parameters(self):
#         print("Video_Path" , self.video_path)
#         print("original_language" , self.original_language)
#         print("target_language" , self.target_language)
#         print("speaking_rate" , self.speaking_rate)

#     def extract_audio(self):
#         aai.settings.api_key = self.aai_api_key
#         video = mp.VideoFileClip(self.video_path)
#         audio = video.audio
#         audio_path = "audio.wav"
#         audio.write_audiofile(audio_path)
#         print("Audio extracted successfully!")
#         return audio_path

#     def gender_detection(self):
#         # gender_model_url = "https://salman11223-gender-detection.hf.space/--replicas/wml9f/"
#         # gender_client = Client(gender_model_url)
#         # gender = gender_client.predict(
#         #     'audio.wav', api_name="/predict"
#         # )
#         # print(gender)
#         # return gender
#         return "male"



#     def org_language_parameters(self,original_language):
#         if original_language == 'English':
#             self.lan_code='en'
#         elif original_language =='German':
#             self.lan_code='de'
#         elif original_language =='French':
#             self.lan_code='fr'
#         elif original_language =='Spanish':
#             self.lan_code='es'
#         else:
#             self.lan_code = ''

#     def set_language_parameters(self, target_language, detected_gender):
#             if target_language == 'English':
#                 self.language_code = 'en-US'
#                 self.trans_code = 'en'
#                 self.voice_names = 'en-US-GuyNeural' if detected_gender == 'male' else 'en-US-AriaNeural'
#             elif target_language == 'German':
#                 self.language_code = 'de-DE'
#                 self.trans_code = 'de'
#                 self.voice_names = 'de-DE-ConradNeural' if detected_gender == 'male' else 'de-DE-KatjaNeural'
#             elif target_language == 'French':
#                 self.language_code = 'fr-CA'
#                 self.trans_code = 'fr'
#                 self.voice_names = 'fr-CA-JeanNeural' if detected_gender == 'male' else 'fr-CA-SylvieNeural'
#             elif target_language == 'Spanish':
#                 self.language_code = 'es-ES'
#                 self.trans_code = 'es'
#                 self.voice_names = 'es-ES-AlvaroNeural' if detected_gender == 'male' else 'es-ES-ElviraNeural'
#             elif target_language == 'Urdu':
#                 self.language_code = 'ur-PK'
#                 self.trans_code = 'ur'
#                 self.voice_names = 'ur-PK-AsadNeural' if detected_gender == 'male' else 'ur-PK-UzmaNeural'
#             else:
#                 # Handle unsupported languages or set default values
#                 self.voice_names = []
#                 self.language_code = ''
#                 self.trans_code = ''


#             print("Target Language:", target_language)
#             print("Trans Code:", self.trans_code)

#     def get_voice_names(self):
#         return self.voice_names

#     def get_language_code(self):
#         return self.language_code



#     def get_audio_duration(self, audio_path):
#         audio_clip = AudioFileClip(audio_path)
#         audio_duration = audio_clip.duration
#         return audio_duration

#     def transcribe_audio(self, audio_path):
#         aai.settings.api_key = self.aai_api_key
#         config = aai.TranscriptionConfig(self.lan_code)
#         transcriber = aai.Transcriber(config=config)
#         transcript = transcriber.transcribe(audio_path)
#         file_path = "transcript.srt"
#         filepath = "t.txt"
#         with open(file_path, "w") as file:
#             file.write(transcript.export_subtitles_srt())
#         with open(filepath, "w") as file:
#             file.write(transcript.text)


#     def generate_ssml(self, text, speaking_rate):
#         # Construct SSML with the given text, speaking rate, voice name, and language code
#         return f'<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="{self.language_code}"><voice name="{self.voice_names}"><prosody rate="{speaking_rate}">{text}</prosody></voice></speak>'
#     def text_to_speech(self, text, apikey, reggion, out_aud_file, speaking_rate):
#         ssml = self.generate_ssml(text, speaking_rate)
#         speech_config = speechsdk.SpeechConfig(subscription=apikey, region=reggion)
#         audio_config = speechsdk.audio.AudioOutputConfig(filename=out_aud_file)
#         speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config, audio_config=audio_config)
#         speech_synthesizer.speak_ssml_async(ssml).get()

#     def translate_text(self, text):
#         base_url = "https://api.cognitive.microsofttranslator.com"
#         endpoint = "/translate"
#         headers = {
#             "Ocp-Apim-Subscription-Key": self.translation_api_key,
#             "Content-Type": "application/json",
#             "Ocp-Apim-Subscription-Region": "southeastasia"
#         }

#         params = {
#             "api-version": "3.0",
#             "to": self.trans_code
#         }
#         body = [{"text": text}]

#         response = requests.post(base_url + endpoint, headers=headers, params=params, json=body)
#         response.raise_for_status()
#         translation = response.json()[0]["translations"][0]["text"]
#         return translation

#     def transcribe_and_translate(self):
#         audio_path = self.extract_audio()
#         self.org_language_parameters(self.original_language)
#         self.transcribe_audio(audio_path)
#         gender = self.gender_detection()
#         print("Detected Gender:", gender)
#         self.set_language_parameters(self.target_language,gender)
#         with open("transcript.srt", 'r') as srt_file:
#             original_srt_content = srt_file.read()

#         original_subtitles = original_srt_content.strip().split('\n\n')

#         translated_subtitles = []
#         for subtitle in original_subtitles:
#             lines = subtitle.split('\n')
#             sequence_number = lines[0]
#             timestamp = lines[1]
#             original_text = '\n'.join(lines[2:])
#             translated_text = self.translate_text(original_text)
#             translated_subtitle = f"{sequence_number}\n{timestamp}\n{translated_text}"
#             translated_subtitles.append(translated_subtitle)

#         translated_srt_content = '\n\n'.join(translated_subtitles)
#         translated_srt_path = "translated_file.srt"

#         with open(translated_srt_path, 'w', encoding='utf-8') as srt_file:
#             srt_file.write(translated_srt_content)

#         # Loop through each translated subtitle and generate speech
#         translated_audio_paths = []
#         for subtitle in translated_subtitles:
#             lines = subtitle.split('\n')
#             sequence_number = lines[0]
#             timestamp = lines[1]
#             translated_text = '\n'.join(lines[2:])
#             translated_audio_path = f"translated_audio_{sequence_number}.wav"
#             self.text_to_speech(translated_text, self.txtospech_key, "southeastasia", translated_audio_path, self.speaking_rate)
#             translated_audio_paths.append(translated_audio_path)

#         # Create a list to store the audio clips
#         translated_audio_clips = []

#         # Loop through each translated audio path and create an AudioFileClip
#         for audio_path in translated_audio_paths:
#             translated_audio_clip = mp.AudioFileClip(audio_path)
#             translated_audio_clips.append(translated_audio_clip)

#         # Concatenate the translated audio clips into a single audio file
#         translated_audio = mp.concatenate_audioclips(translated_audio_clips)

#         # Define the output audio file path
#         output_audio_path = "translated_audio.wav"

#         # Write the concatenated translated audio to the output file
#         translated_audio.write_audiofile(output_audio_path)

#         # Load the original video
#         video = mp.VideoFileClip(self.video_path)

#         # Load the translated audio
#         translated_audio = mp.AudioFileClip(output_audio_path)

#         # Set the audio of the video to the translated audio
#         video = video.set_audio(translated_audio)

#         # Define the output video file path
#         output_video_path = "translated_video.mp4"

#         # Write the video with translated audio to the output file
#         video.write_videofile(output_video_path, codec="libx264", audio_codec="aac")

#         # Clean up temporary files
#         self.cleanup_temp_files()

#     def cleanup_temp_files(self):
#         temp_files = ["audio.wav", "t.txt", "transcript.srt","translated_audio.wav","translated_file.srt"] + [f"translated_audio_{i}.wav" for i in range(1, 100)]  # Adjust the range accordingly
#         for file in temp_files:
#             if os.path.exists(file):
#                 os.remove(file)
#                 print(f"Deleted {file}")