import time, json, gc, math, urllib.request
import torch, numpy as np, soundfile as sf, librosa
print(">>> PHASE 2: running tutorial\n")
print("NumPy:", np.__version__, "| PyTorch:", torch.__version__)
print("CUDA available:", torch.cuda.is_available())
if torch.cuda.is_available():
print("GPU:", torch.cuda.get_device_name(0),
f"| VRAM: {torch.cuda.get_device_properties(0).total_memory/1e9:.1f} GB")
else:
print("⚠️ No GPU — will run on CPU (very slow). "
"Set Runtime > Change runtime type > GPU.")
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
LANGS = {
"bg":"Bulgarian","hr":"Croatian","cs":"Czech","da":"Danish","nl":"Dutch",
"en":"English","et":"Estonian","fi":"Finnish","fr":"French","de":"German",
"el":"Greek","hu":"Hungarian","it":"Italian","lv":"Latvian","lt":"Lithuanian",
"mt":"Maltese","pl":"Polish","pt":"Portuguese","ro":"Romanian","sk":"Slovak",
"sl":"Slovenian","es":"Spanish","sv":"Swedish","ru":"Russian","uk":"Ukrainian",
}
print(f"\nSupported languages ({len(LANGS)}):", ", ".join(LANGS.keys()))
from nemo.collections.asr.models import ASRModel
print("\nLoading nvidia/canary-1b-v2 ...")
t0 = time.time()
asr_model = ASRModel.from_pretrained(model_name="nvidia/canary-1b-v2").to(DEVICE).eval()
print(f"Model loaded in {time.time()-t0:.1f}s")
Credit: Source link
