Update app.py

app.py

@@ -1,63 +1,41 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+import torch
+from transformers import (
+    AutomaticSpeechRecognitionPipeline,
+    WhisperForConditionalGeneration,
+    WhisperTokenizer,
+    WhisperProcessor,
+)
+from peft import PeftModel, PeftConfig
+peft_model_id = "Boadiwaa/LORA-colab-Whisper-medium"
+task = "transcribe"
+peft_config = PeftConfig.from_pretrained(peft_model_id)
+model = WhisperForConditionalGeneration.from_pretrained(
+    peft_config.base_model_name_or_path, load_in_8bit=True, device_map="auto"
+)
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+model = PeftModel.from_pretrained(model, peft_model_id)
+tokenizer = WhisperTokenizer.from_pretrained(peft_config.base_model_name_or_path,task=task)
+processor = WhisperProcessor.from_pretrained(peft_config.base_model_name_or_path,task=task)
+feature_extractor = processor.feature_extractor
+#forced_decoder_ids = processor.get_decoder_prompt_ids(language=language, task=task)
+pipe = AutomaticSpeechRecognitionPipeline(model=model, tokenizer=tokenizer, feature_extractor=feature_extractor)
+
+
+def transcribe(audio):
+    with torch.cuda.amp.autocast():
+        text = pipe(audio,max_new_tokens=255)["text"]
+    return text
+
+demo = gr.Interface(
+    fn=transcribe,
+    inputs=gr.Audio(sources=["microphone"], type="filepath"),
+    outputs="text",
+    title="PEFT LoRA + INT8 Whisper Large V2 Ghanaian accent",
+    description="Realtime demo for Ghanaian-accented speech recognition using `PEFT-LoRA+INT8` fine-tuned Whisper Large V2 model.",
 )
 
+demo.launch(share=True)
 
 if __name__ == "__main__":
     demo.launch()