def compute_mfcc():
featOutDir = os.path.join("exp", "mfcc")
exkaldi.utils.make_dependent_dirs(featOutDir, pathIsFile=False)
for Name in ["train", "dev", "test"]:
print(f"Compute {Name} MFCC feature.")
exkaldi.utils.make_dependent_dirs(os.path.join(featOutDir, Name),
pathIsFile=False)
# Compute feature
feat = exkaldi.compute_mfcc(
wavFile=os.path.join("exp", "data", Name, "wav.scp"),
config={"--use-energy": "false"},
)
feat.save(os.path.join(featOutDir, Name, "raw_mfcc.ark"))
print(f"Generate raw MFCC feature done.")
# Compute CMVN
cmvn = exkaldi.compute_cmvn_stats(
feat=feat,
spk2utt=os.path.join("exp", "data", Name, "spk2utt"),
)
cmvn.save(os.path.join(featOutDir, Name, "cmvn.ark"))
print(f"Generate CMVN statistics done.")
# Apply CMVN
feat = exkaldi.use_cmvn(
feat=feat,
cmvn=cmvn,
utt2spk=os.path.join("exp", "data", Name, "utt2spk"),
)
feat.save(os.path.join(featOutDir, Name, "mfcc_cmvn.ark"))
print(f"Generate MFCC feature (applied CMVN) done.")
print("Compute MFCC done.")
def main():
# ------------- Parse arguments from command line ----------------------
# 1. Add a discription of this program
args.describe(
"This program is used to compute MFCC feature and CMVN statistics")
# 2. Add options
args.add("--expDir",
abbr="-e",
dtype=str,
default="exp",
discription="The data and output path of current experiment.")
args.add("--useEnergy",
abbr="-u",
dtype=bool,
default=False,
discription="Whether add energy to MFCC feature.")
args.add(
"--parallel",
abbr="-p",
dtype=int,
default=4,
minV=1,
maxV=10,
discription=
"The number of parallel process to compute train feature of train dataset."
)
# 3. Then start to parse arguments.
args.parse()
# 4. Take a backup of arguments
args.print_args() # print arguments to display
argsLogFile = os.path.join(args.expDir, "conf", "compute_mfcc.args")
args.save(argsLogFile)
# ---------- Compute mfcc feature of train, dev and test dataset -----------
if args.useEnergy:
mfccConfig = {"--use-energy": "true"}
else:
mfccConfig = {"--use-energy": "false"}
for Name in ["train", "dev", "test"]:
print(f"Compute {Name} MFCC feature.")
# 1. compute feature
if Name == "train" and args.parallel > 1: # use mutiple processes
wavFiles = exkaldi.utils.split_txt_file(
os.path.join(args.expDir, "data", "train", "wav.scp"),
chunks=args.parallel,
)
feats = exkaldi.compute_mfcc(wavFiles,
config=mfccConfig,
outFile=os.path.join(
args.expDir, "mfcc", "train",
"raw_mfcc.ark"))
feat = exkaldi.merge_archives(feats)
else:
feat = exkaldi.compute_mfcc(
os.path.join(args.expDir, "data", Name, "wav.scp"),
config=mfccConfig,
)
feat.save(os.path.join(args.expDir, "mfcc", Name, "raw_mfcc.ark"))
print(f"Generate raw MFCC feature done.")
# Compute CMVN
cmvn = exkaldi.compute_cmvn_stats(
feat=feat,
spk2utt=os.path.join(args.expDir, "data", Name, "spk2utt"),
)
cmvn.save(os.path.join(args.expDir, "mfcc", Name, "cmvn.ark"))
print(f"Generate CMVN statistics done.")
# Apply CMVN
feat = exkaldi.use_cmvn(
feat=feat,
cmvn=cmvn,
utt2spk=os.path.join(args.expDir, "data", Name, "utt2spk"),
)
feat.save(os.path.join(args.expDir, "mfcc", Name, "mfcc_cmvn.ark"))
print(f"Generate MFCC feature (applied CMVN) done.")
print("Compute MFCC done.")
def prepare_DNN_data():
print("Start to prepare data for DNN training")
assert os.path.isdir(f"{args.expDir}/train_sat"
), "Please run previous programs up to SAT training."
# Lexicons and Gmm-Hmm model
lexicons = exkaldi.load_lex(f"{args.expDir}/dict/lexicons.lex")
hmm = f"{args.expDir}/train_sat/final.mdl"
tree = f"{args.expDir}/train_sat/tree"
for Name in ["train", "dev", "test"]:
exkaldi.utils.make_dependent_dirs(
f"{args.expDir}/train_dnn/data/{Name}", pathIsFile=False)
# Make LDA feature
print(f"Make LDA feature for '{Name}'")
feat = exkaldi.load_feat(f"{args.expDir}/mfcc/{Name}/mfcc_cmvn.ark")
feat = feat.splice(left=args.LDAsplice, right=args.LDAsplice)
feat = exkaldi.transform_feat(
feat, matFile=f"{args.expDir}/train_lda_mllt/trans.mat")
# Compile the aligning graph
print(f"Compile aligning graph")
transInt = exkaldi.hmm.transcription_to_int(
transcription=f"{args.expDir}/data/{Name}/text",
symbolTable=lexicons("words"),
unkSymbol=lexicons("oov"),
)
graphFile = exkaldi.decode.wfst.compile_align_graph(
hmm,
tree,
transcription=transInt,
LFile=f"{args.expDir}/dict/L.fst",
outFile=f"{args.expDir}/train_dnn/data/{Name}/align_graph",
lexicons=lexicons,
)
# Align first time
print(f"Align the first time")
ali = exkaldi.decode.wfst.gmm_align(
hmm,
feat,
alignGraphFile=graphFile,
lexicons=lexicons,
)
# Estimate transform matrix
print(f"Estimate fMLLR transform matrix")
fmllrTransMat = exkaldi.hmm.estimate_fMLLR_matrix(
aliOrLat=ali,
lexicons=lexicons,
aliHmm=hmm,
feat=feat,
spk2utt=f"{args.expDir}/data/{Name}/spk2utt",
)
fmllrTransMat.save(f"{args.expDir}/train_dnn/data/{Name}/trans.ark")
# Transform feature
print(f"Transform feature")
feat = exkaldi.use_fmllr(
feat,
fmllrTransMat,
utt2spk=f"{args.expDir}/data/{Name}/utt2spk",
)
# Align second time with new feature
print(f"Align the second time")
ali = exkaldi.decode.wfst.gmm_align(
hmm,
feat,
alignGraphFile=graphFile,
lexicons=lexicons,
)
# Save alignment and feature
print(f"Save final fmllr feature and alignment")
feat.save(f"{args.expDir}/train_dnn/data/{Name}/fmllr.ark")
ali.save(f"{args.expDir}/train_dnn/data/{Name}/ali")
# Transform alignment
print(f"Generate pdf ID and phone ID alignment")
ali.to_numpy(
aliType="pdfID",
hmm=hmm).save(f"{args.expDir}/train_dnn/data/{Name}/pdfID.npy")
ali.to_numpy(
aliType="phoneID",
hmm=hmm).save(f"{args.expDir}/train_dnn/data/{Name}/phoneID.npy")
del ali
# Compute cmvn for fmllr feature
print(f"Compute the CMVN for fmllr feature")
cmvn = exkaldi.compute_cmvn_stats(
feat, spk2utt=f"{args.expDir}/data/{Name}/spk2utt")
cmvn.save(f"{args.expDir}/train_dnn/data/{Name}/cmvn_of_fmllr.ark")
del cmvn
del feat
# copy spk2utt utt2spk and text file
shutil.copyfile(f"{args.expDir}/data/{Name}/spk2utt",
f"{args.expDir}/train_dnn/data/{Name}/spk2utt")
shutil.copyfile(f"{args.expDir}/data/{Name}/utt2spk",
f"{args.expDir}/train_dnn/data/{Name}/utt2spk")
shutil.copyfile(f"{args.expDir}/data/{Name}/text",
f"{args.expDir}/train_dnn/data/{Name}/text")
transInt.save(f"{args.expDir}/data/{Name}/text.int")
print("Write feature and alignment dim information")
dims = exkaldi.ListTable()
feat = exkaldi.load_feat(f"{args.expDir}/train_dnn/data/test/fmllr.ark")
dims["fmllr"] = feat.dim
del feat
hmm = exkaldi.hmm.load_hmm(f"{args.expDir}/train_sat/final.mdl")
dims["phones"] = hmm.info.phones + 1
dims["pdfs"] = hmm.info.pdfs
del hmm
dims.save(f"{args.expDir}/train_dnn/data/dims")
def prepare_LSTM_data():
print("Start to prepare data for LSTM training")
declare.is_dir(f"{args.expDir}/train_dnn/prob", debug="Please run previous programs up to DNN training.")
# Lexicons and Gmm-Hmm model
lexicons = exkaldi.load_lex( f"{args.expDir}/dict/lexicons.lex" )
hmm = f"{args.expDir}/train_sat/final.mdl"
tree = f"{args.expDir}/train_sat/tree"
for Name in ["train", "dev", "test"]:
exkaldi.utils.make_dependent_dirs(f"{args.expDir}/train_lstm/data/{Name}", pathIsFile=False)
# Load feature
print(f"Make LDA feature for '{Name}'")
feat = exkaldi.load_feat( f"{args.expDir}/mfcc/{Name}/mfcc_cmvn.ark" )
feat = feat.splice(left=args.LDAsplice, right=args.LDAsplice)
feat = exkaldi.transform_feat(feat, matFile=f"{args.expDir}/train_lda_mllt/trans.mat" )
# Load probability for aligning( File has a large size, so we use index table. )
prob = exkaldi.load_index_table( f"{args.expDir}/train_dnn/prob/{Name}.ark" )
# Compile a aligning graph
print(f"Copy aligning graph from DNN resources")
shutil.copyfile( f"{args.expDir}/train_dnn/data/{Name}/align_graph",
f"{args.expDir}/train_lstm/data/{Name}/align_graph"
)
# Align
print("Align")
ali = exkaldi.decode.wfst.nn_align(
hmm,
prob,
alignGraphFile=f"{args.expDir}/train_lstm/data/{Name}/align_graph",
lexicons=lexicons,
outFile=f"{args.expDir}/train_lstm/data/{Name}/ali",
)
# Estimate transform matrix
print("Estimate transform matrix")
fmllrTransMat = exkaldi.hmm.estimate_fMLLR_matrix(
aliOrLat=ali,
lexicons=lexicons,
aliHmm=hmm,
feat=feat,
spk2utt=f"{args.expDir}/data/{Name}/spk2utt",
outFile=f"{args.expDir}/train_lstm/data/{Name}/trans.ark",
)
# Transform feature
print("Transform matrix")
feat = exkaldi.use_fmllr(
feat,
fmllrTransMat,
utt2spk=f"{args.expDir}/data/{Name}/utt2spk",
outFile=f"{args.expDir}/train_lstm/data/{Name}/fmllr.ark",
)
# Transform alignment (Because 'ali' is a index table object, we need fetch the alignment data in order to use the 'to_numpy' method.)
ali = ali.fetch(arkType="ali")
ali.to_numpy(aliType="pdfID",hmm=hmm).save( f"{args.expDir}/train_lstm/data/{Name}/pdfID.npy" )
ali.to_numpy(aliType="phoneID",hmm=hmm).save( f"{args.expDir}/train_lstm/data/{Name}/phoneID.npy" )
del ali
# Compute cmvn for fmllr feature
cmvn = exkaldi.compute_cmvn_stats(
feat,
spk2utt=f"{args.expDir}/data/{Name}/spk2utt",
outFile=f"{args.expDir}/train_lstm/data/{Name}/cmvn_of_fmllr.ark",
)
del cmvn
del feat
# copy spk2utt utt2spk and text file
shutil.copyfile( f"{args.expDir}/data/{Name}/spk2utt", f"{args.expDir}/train_lstm/data/{Name}/spk2utt")
shutil.copyfile( f"{args.expDir}/data/{Name}/utt2spk", f"{args.expDir}/train_lstm/data/{Name}/utt2spk")
shutil.copyfile( f"{args.expDir}/data/{Name}/text", f"{args.expDir}/train_lstm/data/{Name}/text" )
print("Write feature and alignment dim information")
dims = exkaldi.ListTable()
feat = exkaldi.load_feat( f"{args.expDir}/train_lstm/data/test/fmllr.ark" )
dims["fmllr"] = feat.dim
del feat
hmm = exkaldi.hmm.load_hmm( f"{args.expDir}/train_sat/final.mdl" )
dims["phones"] = hmm.info.phones + 1
dims["pdfs"] = hmm.info.pdfs
del hmm
dims.save( f"{args.expDir}/train_lstm/data/dims" )