Spaces:
Runtime error
Runtime error
File size: 1,350 Bytes
36d155d 1378b33 36d155d 1378b33 36d155d 1378b33 |
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 48 49 |
import gradio as gr
import json
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
max_new_tokens=128,
chunk_length_s=30,
batch_size=16,
return_timestamps=True,
torch_dtype=torch_dtype,
device=device,
)
def process_audio(audio_file):
# In this example, let's just return a hardcoded array of JSON objects
output_data = [
{"label": "cat", "confidence": 0.8},
{"label": "dog", "confidence": 0.7},
{"label": "bird", "confidence": 0.6}
]
return json.dumps(output_data)
def process(audio):
result = pipe('audio.mp3')['chunks']
for item in result:
item['timestamp'] = list(item['timestamp'])
return result
iface = gr.Interface(fn=process_audio, inputs="audio", outputs="text")
iface.launch()
|