File size: 5,743 Bytes
b368e21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
Created By: ishwor subedi
Date: 2024-07-31
"""
import os
import tempfile
from fastapi.responses import JSONResponse
from fastapi import Form
from fastapi import UploadFile, HTTPException, status
from src.models.models import TextToSpeechRequest
from fastapi.routing import APIRouter
from src.pipeline.speech_transcription_pipeline import SpeechTranscriptionPipeline
from src import logging

speech_translator_router = APIRouter(tags=["SpeechTranscription"])
pipeline = SpeechTranscriptionPipeline()


@speech_translator_router.post(
    "/text_to_speech",
    description="""
    ** For language refer below points**
    **Supported Locales:**

    - **English:**
      - **Australia:** 
        - **Language:** en
        - **TLD:** com.au
      - **United Kingdom:**
        - **Language:** en
        - **TLD:** co.uk
      - **United States:**
        - **Language:** en
        - **TLD:** us
      - **Canada:**
        - **Language:** en
        - **TLD:** ca
      - **India:**
        - **Language:** en
        - **TLD:** co.in
      - **Ireland:**
        - **Language:** en
        - **TLD:** ie
      - **South Africa:**
        - **Language:** en
        - **TLD:** co.za
      - **Nigeria:**
        - **Language:** en
        - **TLD:** com.ng

    - **French:**
      - **Canada:** 
        - **Language:** fr
        - **TLD:** ca
      - **France:**
        - **Language:** fr
        - **TLD:** fr

    - **Mandarin:**
      - **China Mainland:** 
        - **Language:** zh-CN
        - **TLD:** any
      - **Taiwan:**
        - **Language:** zh-TW
        - **TLD:** any

    - **Portuguese:**
      - **Brazil:** 
        - **Language:** pt
        - **TLD:** com.br
      - **Portugal:**
        - **Language:** pt
        - **TLD:** pt

    - **Spanish:**
      - **Mexico:** 
        - **Language:** es
        - **TLD:** com.mx
      - **Spain:**
        - **Language:** es
        - **TLD:** es
      - **United States:**
        - **Language:** es
        - **TLD:** us
    """
)
async def text_to_speech(request: TextToSpeechRequest):
    logging.info(f"Text to speech request received")
    try:
        audio_bytes = pipeline.text_to_speech(request.text, request.lang, request.tld)
        if not audio_bytes:
            logging.error(f"Audio generation failed.")
            raise ValueError("Audio generation failed.")
        logging.info(f"Text to speech request processed successfully")
        return JSONResponse(content={"audio": audio_bytes, "status_code": status.HTTP_200_OK}, status_code=200)
    except ValueError as ve:
        logging.error(f"Error processing text to speech request: {str(ve)}")
        raise HTTPException(status_code=400, detail=str(ve))
    except Exception as e:
        logging.error(f"Internal Server Error: {str(e)}")
        raise HTTPException(status_code=500, detail="Internal Server Error")


@speech_translator_router.post(
    "/speech_to_text",
    description="""
    ** Specify the language used in the audio **
    **Supported Languages:**

    **Major Languages:**
    - **English:** en
    - **Mandarin Chinese:** zh
    - **Spanish:** es
    - **French:** fr
    - **German:** de
    - **Italian:** it
    - **Japanese:** ja
    - **Korean:** ko
    - **Russian:** ru
    - **Portuguese:** pt
    - **Arabic:** ar

    **Additional Languages:**

    - **Indic Languages:**
      - **Hindi:** hi
      - **Bengali:** bn
      - **Tamil:** ta
      - **Telugu:** te

    - **Southeast Asian Languages:**
      - **Vietnamese:** vi
      - **Thai:** th
      - **Indonesian:** id
      - **Malay:** ms

    - **African Languages:**
      - **Swahili:** sw
      - **Yoruba:** yo
      - **Hausa:** ha

    - **European Languages:**
      - **Polish:** pl
      - **Dutch:** nl
      - **Swedish:** sv
      - **Norwegian:** no
    """
)
async def speech_to_text(audio: UploadFile, lang: str = Form(...)):
    logging.info(f"Speech to text request received")
    try:
        audio_bytes = await audio.read()
        if not audio_bytes:
            logging.error(f"Empty audio file")
            raise ValueError("Empty audio file")
    except Exception as e:
        logging.error(f"Invalid audio file {e}")
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
            detail="Invalid audio file"
        )

    try:
        with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_audio_file:
            temp_audio_file.write(audio_bytes)
            temp_audio_file_path = temp_audio_file.name
            logging.info(f"Temporary audio file created at {temp_audio_file_path}")
    except Exception as e:
        logging.error(f"Could not process audio file{e}")
        raise HTTPException(
            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
            detail="Could not process audio file"
        )

    try:
        logging.info(f"Transcribing audio to text")
        transcript = pipeline.speech_to_text(temp_audio_file_path, lang)
    except FileNotFoundError as fnfe:
        logging.error(f"Temporary file not found{fnfel}")
        raise HTTPException(
            status_code=status.HTTP_404_NOT_FOUND,
            detail="Temporary file not found"
        )
    except Exception as e:
        logging.error(f"Error processing speech-to-text: {str(e)}")
        raise HTTPException(
            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
            detail="Error processing speech-to-text"
        )
    finally:
        logging.info(f"Cleaning up temporary audio file")
        if os.path.exists(temp_audio_file_path):
            os.remove(temp_audio_file_path)

    return JSONResponse(content={"transcript": transcript, "status_code": status.HTTP_200_OK}, status_code=200)