Spaces:
Runtime error
Runtime error
File size: 1,199 Bytes
927023e |
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 |
from transformers import pipeline
import torch
device = "cuda:0" if torch.cuda.is_available() else "cpu"
classifier = pipeline(
"audio-classification", model="MIT/ast-finetuned-speech-commands-v2", device=device
)
from transformers.pipelines.audio_utils import ffmpeg_microphone_live
def launch_fn(
wake_word="marvin",
prob_threshold=0.5,
chunk_length_s=2.0,
stream_chunk_s=0.25,
debug=False,
):
if wake_word not in classifier.model.config.label2id.keys():
raise ValueError(
f"Wake word {wake_word} not in set of valid class labels, pick a wake word in the set {classifier.model.config.label2id.keys()}."
)
sampling_rate = classifier.feature_extractor.sampling_rate
mic = ffmpeg_microphone_live(
sampling_rate=sampling_rate,
chunk_length_s=chunk_length_s,
stream_chunk_s=stream_chunk_s,
)
print("Listening for wake word...")
for prediction in classifier(mic):
prediction = prediction[0]
if debug:
print(prediction)
if prediction["label"] == wake_word:
if prediction["score"] > prob_threshold:
return True
launch_fn(debug=True) |