File size: 14,549 Bytes
8031a8f 27acc7d 8031a8f 27acc7d 8031a8f 27acc7d 8031a8f 27acc7d 8031a8f 27acc7d 8031a8f 27acc7d 8031a8f 27acc7d 8031a8f |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 |
from fastapi import FastAPI, UploadFile, File, Form , HTTPException
from fastapi.responses import JSONResponse
from fastapi.middleware.cors import CORSMiddleware
import sys
import os
import shutil
import uuid
# Ensure sibling module fluency is discoverable
#sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
from fluency.fluency_api import main as analyze_fluency_main
from tone_modulation.tone_api import main as analyze_tone_main
from vcs.vcs_api import main as analyze_vcs_main
from vers.vers_api import main as analyze_vers_main
from voice_confidence_score.voice_confidence_api import main as analyze_voice_confidence_main
from vps.vps_api import main as analyze_vps_main
from ves.ves import calc_voice_engagement_score
from transcribe import transcribe_audio
from filler_count.filler_score import analyze_fillers
from emotion.emo_predict import predict_emotion
app = FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"], # In production, replace "*" with allowed frontend domains
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
@app.post("/analyze_fluency/")
async def analyze_fluency(file: UploadFile):
# idk if we can use pydantic model here If we need I can add later
if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path for temporary storage of the uploaded file this will be deleted after processing
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
result = analyze_fluency_main(temp_filepath, model_size="base")
return JSONResponse(content=result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Fluency analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
@app.post('/analyze_tone/')
async def analyze_tone(file: UploadFile):
"""
Endpoint to analyze tone of an uploaded audio file (.wav or .mp3).
"""
if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Analyze tone using your custom function
result = analyze_tone_main(temp_filepath)
return JSONResponse(content=result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Tone analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
@app.post('/analyze_vcs/')
async def analyze_vcs(file: UploadFile):
"""
Endpoint to analyze voice clarity of an uploaded audio file (.wav or .mp3).
"""
if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Analyze voice clarity using your custom function
result = analyze_vcs_main(temp_filepath)
return JSONResponse(content=result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Voice clarity analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
@app.post('/analyze_vers/')
async def analyze_vers(file: UploadFile):
"""
Endpoint to analyze VERS of an uploaded audio file (.wav or .mp3).
"""
if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Analyze VERS using your custom function
result = analyze_vers_main(temp_filepath)
return JSONResponse(content=result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"VERS analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
@app.post('/voice_confidence/')
async def analyze_voice_confidence(file: UploadFile):
"""
Endpoint to analyze voice confidence of an uploaded audio file (.wav or .mp3).
"""
if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Analyze voice confidence using your custom function
result = analyze_voice_confidence_main(temp_filepath)
return JSONResponse(content=result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Voice confidence analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
@app.post('/analyze_vps/')
async def analyze_vps(file: UploadFile):
"""
Endpoint to analyze voice pacing score of an uploaded audio file (.wav or .mp3).
"""
if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Analyze voice pacing score using your custom function
result = analyze_vps_main(temp_filepath)
return JSONResponse(content=result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Voice pacing score analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
@app.post('/voice_engagement_score/')
async def analyze_voice_engagement_score(file: UploadFile):
"""
Endpoint to analyze voice engagement score of an uploaded audio file (.wav or .mp3).
"""
if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Analyze voice engagement score using your custom function
result = calc_voice_engagement_score(temp_filepath)
return JSONResponse(content=result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Voice engagement score analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
@app.post('/analyze_fillers/')
async def analyze_fillers_count(file: UploadFile):
"""
Endpoint to analyze filler words in an uploaded audio file (.wav or .mp3).
"""
if not file.filename.endswith(('.wav', '.mp3','.mp4','.m4a','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Call the analysis function with the file path
result = analyze_fillers(temp_filepath) # Pass the file path, not the UploadFile object
return JSONResponse(content=result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Filler analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
import time
@app.post('/transcribe/')
async def transcribe(file: UploadFile, language: str = Form(...)):
"""
Endpoint to transcribe an uploaded audio file (.wav or .mp3).
"""
#calculate time to transcribe
start_time = time.time()
if not file.filename.endswith(('.wav', '.mp3','mp4','.m4a','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav ,mp4 and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Transcribe using your custom function
result = transcribe_audio(temp_filepath, language=language, model_size="base")
end_time = time.time()
transcription_time = end_time - start_time
response = {
"transcription": result,
"transcription_time": transcription_time
}
return JSONResponse(content=response)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Transcription failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
@app.post('/analyze_all/')
async def analyze_all(file: UploadFile, language: str = Form(...)):
"""
Endpoint to analyze all aspects of an uploaded audio file (.wav or .mp3).
"""
if not file.filename.endswith(('.wav', '.mp3','.m4a','.mp4','.flac')):
raise HTTPException(status_code=400, detail="Invalid file type. Only .wav and .mp3 files are supported.")
# Generate a safe temporary file path
temp_filename = f"temp_{uuid.uuid4()}{os.path.splitext(file.filename)[1]}"
temp_dir = "temp_uploads"
temp_filepath = os.path.join(temp_dir, temp_filename)
os.makedirs(temp_dir, exist_ok=True)
try:
# Save uploaded file
with open(temp_filepath, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
# Analyze all aspects using your custom functions
fluency_result = analyze_fluency_main(temp_filepath, model_size="base")
tone_result = analyze_tone_main(temp_filepath)
vcs_result = analyze_vcs_main(temp_filepath)
vers_result = analyze_vers_main(temp_filepath)
voice_confidence_result = analyze_voice_confidence_main(temp_filepath)
vps_result = analyze_vps_main(temp_filepath)
ves_result = calc_voice_engagement_score(temp_filepath)
filler_count = analyze_fillers(temp_filepath) # Assuming this function returns a dict with filler count
transcript = transcribe_audio(temp_filepath, language, "base") #fix this
emotion = predict_emotion(temp_filepath)
avg_score = (fluency_result['fluency_score'] + tone_result['speech_dynamism_score'] + vcs_result['Voice Clarity Sore'] + vers_result['VERS Score'] + voice_confidence_result['voice_confidence_score'] + vps_result['VPS'] + ves_result['ves']) / 7
# Combine results into a single response
combined_result = {
"fluency": fluency_result,
"tone": tone_result,
"vcs": vcs_result,
"vers": vers_result,
"voice_confidence": voice_confidence_result,
"vps": vps_result,
"ves": ves_result,
"filler_words": filler_count,
"transcript": transcript,
"emotion": emotion ,
"sank_score": avg_score
}
return JSONResponse(content=combined_result)
except Exception as e:
raise HTTPException(status_code=500, detail=f"Analysis failed: {str(e)}")
finally:
# Clean up temporary file
if os.path.exists(temp_filepath):
os.remove(temp_filepath)
|