File size: 1,593 Bytes
1e5cce1 0330954 1e5cce1 2a63b9e 1e5cce1 285256f 1e5cce1 0229275 1e5cce1 b999686 7dbe2e1 1e5cce1 7dbe2e1 3a0e917 7dbe2e1 add7e1d 78d6df1 |
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 |
import json
import requests
import os
import traceback
import gradio as gr # Imports the Gradio library, which is used to create user interfaces for machine learning models.
HF_TOKEN = os.environ.get("HF_TOKEN", None)
API_URL = "https://api-inference.huggingface.co/models/"
def s2t(audio, model_name):
with open(audio, "rb") as f:
data = f.read()
try:
url = API_URL + model_name
headers = {"Authorization": f"Bearer {HF_TOKEN}"}
response = requests.request("POST", url, headers=headers, data=data)
text = json.loads(response.content.decode("utf-8"))
text = text['text']
except:
text = f"Transcription failed with error：\n{traceback.format_exc()}"
yield text
with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
model_name = gr.Dropdown(
label="Models:",
choices=[
"openai/whisper-large-v3",
"openai/whisper-large-v2",
"openai/whisper-large",
"openai/whisper-medium",
"openai/whisper-small",
"openai/whisper-base",
"openai/whisper-tiny",
],
value="openai/whisper-large-v3",
)
audio = gr.Audio(sources=["microphone","upload"], type="filepath", label="Audio")
with gr.Column():
output = gr.Textbox(label="Transcription results")
audio.change(s2t, inputs=[audio, model_name], outputs=output)
demo.launch() |