File size: 890 Bytes
7d0471b 2f6c921 1e24584 00f4803 2f6c921 013bd79 2f6c921 013bd79 013ee0a 81b844f 013bd79 2f6c921 7d0471b 75fd29e 81b844f 7d0471b |
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 |
import os
os.system("pip install git+https://github.com/openai/whisper.git")
import gradio as gr
import whisper
import torch
import gradio as gr
from transformers import GPT2Tokenizer, GPT2LMHeadModel
# Load tokenizer and model
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
model2 = GPT2LMHeadModel.from_pretrained("gpt2")
#LOAD THE MODEL
model = whisper.load_model("base")
def speech_to_text(inp):
result = model.transcribe(inp)
input_ids = tokenizer.encode(result["text"], return_tensors="pt")
output = model2.generate(input_ids, max_length=50, num_return_sequences=1, early_stopping=True)
decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
return decoded_output
#LAUNCH THE UI WITH GRADIO
interface = gr.Interface(
fn=speech_to_text,
inputs=[gr.Audio(type="filepath")],
outputs="text",
)
interface.launch(share=True)
|