Spaces:
Sleeping
Sleeping
File size: 1,396 Bytes
e828a9f dd4c06b 52cfee9 8607936 dd4c06b 043229b 52cfee9 a4e4751 8607936 52cfee9 a4e4751 8607936 a4e4751 8607936 dd4c06b e828a9f 8607936 |
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 spaces
import gradio as gr
# Use a pipeline as a high-level helper
import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
@spaces.GPU(duration=120)
def transcribe_audio(audio):
if audio is None:
return "Please upload an audio file."
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", "alvanlii/whisper-small-cantonese"]
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=25,
batch_size=16,
torch_dtype=torch_dtype,
device=device,
)
result = pipe(audio)
return result["text"]
demo = gr.Interface(fn=transcribe_audio,
inputs=[gr.Audio(sources="upload", type="filepath"), gr.Dropdown(choices=["openai/whisper-large-v3", "alvanlii/whisper-small-cantonese"])],
outputs="text")
demo.launch()
|