def prepare_data(training=True):
if training:
flag = "train_clean_5"
else:
flag = "dev_clean_2"
print(f"{flag}: Load feature...")
featsFile = f"{args.root}/{args.feat}/raw_{args.feat}_{flag}.*.ark"
feats = exkaldi.load_feat(featsFile)
if args.cmn:
print(f"{flag}: Use cmvn...")
cmvnFile = f"{args.root}/{args.feat}/cmvn_{flag}.ark"
cmvn = exkaldi.load_cmvn(cmvnFile)
feats = exkaldi.use_cmvn(feats,
cmvn,
utt2spk=f"{args.root}/data/{flag}/utt2spk")
del cmvn
if args.delta > 0:
print(f"{flag}: Add delta...")
feats = feats.add_delta(args.delta)
if args.splice > 0:
print(f"{flag}: Splice feature...")
feats = feats.splice(args.splice)
feats = feats.to_numpy()
featDim = feats.dim
print(f"{flag}: Load alignment...")
ali = exkaldi.load_ali(f"{args.feat}/exp/tri3b_ali_{flag}/ali.*.gz")
print(f"{flag}: Get pdf alignment...")
pdfAli = ali.to_numpy(aliType="pdfID",
hmm=f"{args.feat}/exp/tri3b_ali_{flag}/final.mdl")
del ali
feats.rename("feat")
pdfAli.rename("pdfID")
#phoneAli.rename("phoneID")
print(f"{flag}: Tuple dataset...")
dataset = exkaldi.tuple_dataset([feats, pdfAli], frameLevel=True)
random.shuffle(dataset)
return featDim, dataset
def tuple_dataset(feat,pdfAli,phoneAli,cutLength=None):
if cutLength is not None:
newFeat = feat.cut(cutLength).sort(by="frame")
newPdfAli = pdfAli.cut(cutLength).sort(by="frame")
newPhoneAli = phoneAli.cut(cutLength).sort(by="frame")
else:
newFeat = feat.sort(by="frame")
newPdfAli = pdfAli.sort(by="frame")
newPhoneAli = phoneAli.sort(by="frame")
newFeat.rename("feat")
newPdfAli.rename("pdfID")
newPhoneAli.rename("phoneID")
dataset = exkaldi.tuple_dataset([newFeat, newPdfAli, newPhoneAli], frameLevel=False)
return dataset
def process_feat_ali(training=True):
if training:
Name = "train"
else:
Name = "dev"
feat = exkaldi.load_feat(f"{args.expDir}/train_dnn/data/{Name}/fmllr.ark")
if args.useCMVN:
cmvn = exkaldi.load_cmvn(
f"{args.expDir}/train_dnn/data/{Name}/cmvn_of_fmllr.ark")
feat = exkaldi.use_cmvn(
feat, cmvn, f"{args.expDir}/train_dnn/data/{Name}/utt2spk")
del cmvn
if args.delta > 0:
feat = feat.add_delta(args.delta)
if args.splice > 0:
feat = feat.splice(args.splice)
feat = feat.to_numpy()
if args.normalizeFeat:
feat = feat.normalize(std=True)
pdfAli = exkaldi.load_ali(f"{args.expDir}/train_dnn/data/{Name}/pdfID.npy")
phoneAli = exkaldi.load_ali(
f"{args.expDir}/train_dnn/data/{Name}/phoneID.npy")
feat.rename("feat")
pdfAli.rename("pdfID")
phoneAli.rename("phoneID")
dataset = exkaldi.tuple_dataset([feat, pdfAli, phoneAli], frameLevel=True)
random.shuffle(dataset)
return dataset