app.py

from transformers import pipeline
import gradio as gr

pipe = pipeline(model="jsbeaudry/creole-speech-to-text")  

def transcribe(audio):
    text = pipe(audio)["text"]
    return text


iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(type="filepath"), 
    outputs="text",
    title="Whisper medium Creole",
    description="Realtime demo for Haitian Creole speech recognition using a fine-tuned medium small model.",
)

iface.launch()



# from transformers import pipeline
# import gradio as gr

# import torch
# from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
# from datasets import load_dataset


# device = "cuda:0" if torch.cuda.is_available() else "cpu"
# torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

# model_id = "jsbeaudry/creole-speech-to-text"

# model = AutoModelForSpeechSeq2Seq.from_pretrained(
#     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
# )
# model.to(device)

# processor = AutoProcessor.from_pretrained(model_id)

# pipe = pipeline(
#     "automatic-speech-recognition",
#     model=model,
#     tokenizer=processor.tokenizer,
#     feature_extractor=processor.feature_extractor,
#     torch_dtype=torch_dtype,
#     device=device,
# )
# def transcribe(audio):
#     # Use the 'whisper' pipeline defined in the previous cell
#     text = pipe(audio)["text"]
#     return text

# iface = gr.Interface(
#     fn=transcribe,
#     inputs=gr.Audio(type="filepath"),
#     outputs="text",
#     title="Whisper medium Creole",
#     description="Realtime demo for Haitian Creole speech recognition using a fine-tuned medium small model.",
# )

# iface.launch()