mulasagg commited on
Commit
9740f3b
·
1 Parent(s): e4b8438

fix language issue

Browse files
Files changed (2) hide show
  1. app.py +11 -11
  2. transcribe.py +1 -1
app.py CHANGED
@@ -1,4 +1,4 @@
1
- from fastapi import FastAPI, UploadFile, File, Form, HTTPException
2
  from fastapi.responses import JSONResponse
3
  from fastapi.middleware.cors import CORSMiddleware
4
  import sys
@@ -32,7 +32,7 @@ app.add_middleware(
32
  @app.post("/analyze_fluency/")
33
  async def analyze_fluency(file: UploadFile):
34
  # idk if we can use pydantic model here If we need I can add later
35
- if not file.filename.endswith(('.wav', '.mp3')):
36
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
37
 
38
  # Generate a safe temporary file path for temporary storage of the uploaded file this will be deleted after processing
@@ -64,7 +64,7 @@ async def analyze_tone(file: UploadFile):
64
  """
65
  Endpoint to analyze tone of an uploaded audio file (.wav or .mp3).
66
  """
67
- if not file.filename.endswith(('.wav', '.mp3')):
68
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
69
 
70
  # Generate a safe temporary file path
@@ -96,7 +96,7 @@ async def analyze_vcs(file: UploadFile):
96
  """
97
  Endpoint to analyze voice clarity of an uploaded audio file (.wav or .mp3).
98
  """
99
- if not file.filename.endswith(('.wav', '.mp3')):
100
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
101
 
102
  # Generate a safe temporary file path
@@ -128,7 +128,7 @@ async def analyze_vers(file: UploadFile):
128
  """
129
  Endpoint to analyze VERS of an uploaded audio file (.wav or .mp3).
130
  """
131
- if not file.filename.endswith(('.wav', '.mp3')):
132
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
133
 
134
  # Generate a safe temporary file path
@@ -160,7 +160,7 @@ async def analyze_voice_confidence(file: UploadFile):
160
  """
161
  Endpoint to analyze voice confidence of an uploaded audio file (.wav or .mp3).
162
  """
163
- if not file.filename.endswith(('.wav', '.mp3')):
164
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
165
 
166
  # Generate a safe temporary file path
@@ -192,7 +192,7 @@ async def analyze_vps(file: UploadFile):
192
  """
193
  Endpoint to analyze voice pacing score of an uploaded audio file (.wav or .mp3).
194
  """
195
- if not file.filename.endswith(('.wav', '.mp3')):
196
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
197
 
198
  # Generate a safe temporary file path
@@ -224,7 +224,7 @@ async def analyze_voice_engagement_score(file: UploadFile):
224
  """
225
  Endpoint to analyze voice engagement score of an uploaded audio file (.wav or .mp3).
226
  """
227
- if not file.filename.endswith(('.wav', '.mp3')):
228
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
229
 
230
  # Generate a safe temporary file path
@@ -256,7 +256,7 @@ async def analyze_fillers_count(file: UploadFile):
256
  """
257
  Endpoint to analyze filler words in an uploaded audio file (.wav or .mp3).
258
  """
259
- if not file.filename.endswith(('.wav', '.mp3','.mp4')):
260
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
261
 
262
  # Generate a safe temporary file path
@@ -295,7 +295,7 @@ async def transcribe(file: UploadFile, language: str = Form(...)):
295
  """
296
  #calculate time to transcribe
297
  start_time = time.time()
298
- if not file.filename.endswith(('.wav', '.mp3','mp4')):
299
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav ,mp4 and .mp3 files are supported.")
300
 
301
  # Generate a safe temporary file path
@@ -334,7 +334,7 @@ async def analyze_all(file: UploadFile, language: str = Form(...)):
334
  """
335
  Endpoint to analyze all aspects of an uploaded audio file (.wav or .mp3).
336
  """
337
- if not file.filename.endswith(('.wav', '.mp3')):
338
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
339
 
340
  # Generate a safe temporary file path
 
1
+ from fastapi import FastAPI, UploadFile, File, Form , HTTPException
2
  from fastapi.responses import JSONResponse
3
  from fastapi.middleware.cors import CORSMiddleware
4
  import sys
 
32
  @app.post("/analyze_fluency/")
33
  async def analyze_fluency(file: UploadFile):
34
  # idk if we can use pydantic model here If we need I can add later
35
+ if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
36
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
37
 
38
  # Generate a safe temporary file path for temporary storage of the uploaded file this will be deleted after processing
 
64
  """
65
  Endpoint to analyze tone of an uploaded audio file (.wav or .mp3).
66
  """
67
+ if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
68
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
69
 
70
  # Generate a safe temporary file path
 
96
  """
97
  Endpoint to analyze voice clarity of an uploaded audio file (.wav or .mp3).
98
  """
99
+ if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
100
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
101
 
102
  # Generate a safe temporary file path
 
128
  """
129
  Endpoint to analyze VERS of an uploaded audio file (.wav or .mp3).
130
  """
131
+ if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
132
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
133
 
134
  # Generate a safe temporary file path
 
160
  """
161
  Endpoint to analyze voice confidence of an uploaded audio file (.wav or .mp3).
162
  """
163
+ if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
164
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
165
 
166
  # Generate a safe temporary file path
 
192
  """
193
  Endpoint to analyze voice pacing score of an uploaded audio file (.wav or .mp3).
194
  """
195
+ if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
196
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
197
 
198
  # Generate a safe temporary file path
 
224
  """
225
  Endpoint to analyze voice engagement score of an uploaded audio file (.wav or .mp3).
226
  """
227
+ if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
228
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
229
 
230
  # Generate a safe temporary file path
 
256
  """
257
  Endpoint to analyze filler words in an uploaded audio file (.wav or .mp3).
258
  """
259
+ if not file.filename.endswith(('.wav', '.mp3','.mp4','.m4a','.flac')):
260
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
261
 
262
  # Generate a safe temporary file path
 
295
  """
296
  #calculate time to transcribe
297
  start_time = time.time()
298
+ if not file.filename.endswith(('.wav', '.mp3','mp4','.m4a','.flac')):
299
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav ,mp4 and .mp3 files are supported.")
300
 
301
  # Generate a safe temporary file path
 
334
  """
335
  Endpoint to analyze all aspects of an uploaded audio file (.wav or .mp3).
336
  """
337
+ if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
338
  raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
339
 
340
  # Generate a safe temporary file path
transcribe.py CHANGED
@@ -8,7 +8,7 @@ def transcribe_audio(file_path: str, language, model_size=None) -> str:
8
  print(f"Transcribing audio file: {file_path} with language: {language}")
9
  # Configure for Hindi language
10
  config = aai.TranscriptionConfig(
11
- speech_model=aai.SpeechModel.best,
12
  language_code=language
13
  )
14
 
 
8
  print(f"Transcribing audio file: {file_path} with language: {language}")
9
  # Configure for Hindi language
10
  config = aai.TranscriptionConfig(
11
+ speech_model=aai.SpeechModel.nano,
12
  language_code=language
13
  )
14