Spaces:
Runtime error
Runtime error
File size: 1,288 Bytes
e130e80 92f8ba8 e130e80 92f8ba8 e130e80 92f8ba8 e130e80 515a989 e130e80 92f8ba8 e130e80 515a989 e130e80 |
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 |
import gradio as gr
from transformers import pipeline
model_name = "juliensimon/wav2vec2-conformer-rel-pos-large-finetuned-speech-commands"
p = pipeline("audio-classification", model=model_name)
def process(file):
pred = p(file)
return {x["label"]: x["score"] for x in pred}
# Gradio inputs
mic = gr.inputs.Audio(source="microphone", type="filepath", label="Speech input")
# Gradio outputs
labels = gr.outputs.Label(num_top_classes=3)
description = "This Space showcases a wav2vec2-conformer-rel-pos-large model fine-tuned for audio classification on the speech_commands dataset. \n \n It can spot one of the following keywords: 'Yes', 'No', 'Up', 'Down', 'Left', 'Right', 'On', 'Off', 'Stop', 'Go', 'Zero', 'One', 'Two', 'Three', 'Four', 'Five', 'Six', 'Seven', 'Eight', 'Nine', 'Bed', 'Bird', 'Cat', 'Dog', 'Happy', 'House', 'Marvin', 'Sheila', 'Tree', 'Wow', 'Backward', 'Forward', 'Follow', 'Learn', 'Visual'."
iface = gr.Interface(
theme="huggingface",
description=description,
fn=process,
inputs=[mic],
outputs=[labels],
examples=[
["backward16k.wav"],
["happy16k.wav"],
["marvin16k.wav"],
["seven16k.wav"],
["stop16k.wav"],
["up16k.wav"],
],
allow_flagging="never",
)
iface.launch()
|