Update app.py

app.py

@@ -7,24 +7,33 @@ from fastapi.responses import FileResponse
 #from pyannote.audio import Pipeline
  
 from transformers import pipeline # le framework de huggingface
+#from datasets import load_dataset, Audio # ça c'est pour entrainer mon modele
+
 
 app = FastAPI()
 
 #pipe_flan = pipeline("text2text-generation", model="google/flan-t5-small")
-classifier = pipeline("automatic-speech-recognition")# la liste des pipelines de huggingface est disponible ici :https://huggingface.co/docs/transformers/quicktour
-@app.get("/")
-def t5():
+#deepneurones = pipeline("automatic-speech-recognition")# la liste des pipelines de huggingface est disponible ici :https://huggingface.co/docs/transformers/quicktour. pipeline() telecharge dans un cache local le modele deeplearning
+deepneurones= pipeline("automatic-speech-recognition", model="facebook/wav2vec2-base-960h")
+
+@app.get("/healthcheck")
+def healthcheck():
     
     #output = pipe_flan(input)
     #pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization")
     #pipeline("file.wav")
     return {"output":"OK"}
+@app.get("/en")
+def stt(input):
 
+    dataset = load_dataset("PolyAI/minds14", name="en-US", split="train")
+    results = deepneurones(input)
+    return {"output":results}
 #app.mount("/", StaticFiles(directory="static", html=True), name="static")
 
-# @app.get("/")
-#def index() -> FileResponse:
-#    return FileResponse(path="/app/static/index.html", media_type="text/html")
+@app.get("/")
+def index() -> FileResponse:
+    return FileResponse(path="/index.html", media_type="text/html")