You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
While running the asr_prep_json.py code in fairseq/examples/datasets I am getting exception of failed to decode the audio for few of .wav files. I don't understand why I am getting this error.I tried searching it in the existing issues and also on torchaudio but I still don't find kindly let me know how to fixthis.
Code
from future import absolute_import, division, print_function, unicode_literals
import argparse
import concurrent.futures
import json
import multiprocessing
import os
from collections import namedtuple
from itertools import chain
import sentencepiece as spm
from fairseq.data import Dictionary
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"--audio-dirs",
nargs="+",
default=["-"],
required=True,
help="input directories with audio files",
)
parser.add_argument(
"--labels",
required=True,
help="aggregated input labels with format per line",
type=argparse.FileType("r", encoding="UTF-8"),
)
parser.add_argument(
"--spm-model",
required=True,
help="sentencepiece model to use for encoding",
type=argparse.FileType("r", encoding="UTF-8"),
)
parser.add_argument(
"--dictionary",
required=True,
help="file to load fairseq dictionary from",
type=argparse.FileType("r", encoding="UTF-8"),
)
parser.add_argument("--audio-format", choices=["flac", "wav"], default="wav")
parser.add_argument(
"--output",
required=True,
type=argparse.FileType("w"),
help="path to save json output",
)
args = parser.parse_args()
sp = spm.SentencePieceProcessor()
sp.Load(args.spm_model.name)
tgt_dict = Dictionary.load(args.dictionary)
labels = {}
for line in args.labels:
#print(line.split(" ", 1))
(utt_id, label) = line.split(" ", 1)
labels[utt_id] = label
if len(labels) == 0:
raise Exception("No labels found in ", args.labels_path)
Sample = namedtuple("Sample", "aud_path utt_id")
samples = []
for path, _, files in chain.from_iterable(
os.walk(path) for path in args.audio_dirs
):
for f in files:
if f.endswith(args.audio_format):
if len(os.path.splitext(f)) != 2:
raise Exception("Expect <utt_id.extension> file name. Got: ", f)
utt_id = os.path.splitext(f)[0]
if utt_id not in labels:
continue
samples.append(Sample(os.path.join(path, f), utt_id))
utts = {}
num_cpu = multiprocessing.cpu_count()
with concurrent.futures.ThreadPoolExecutor(max_workers=num_cpu) as executor:
future_to_sample = {
executor.submit(
process_sample, s.aud_path, labels[s.utt_id], s.utt_id, sp, tgt_dict
): s
for s in samples
}
for future in concurrent.futures.as_completed(future_to_sample):
url = future_to_sample[future]
try:
data = future.result()
except Exception as exc:
#print(data)
print("generated an exception: ", exc,url)
else:
utts.update(data)
json.dump({"utts": utts}, args.output, indent=4)
if name == "main":
main()
What have you tried?
I tried printing the audios which is causing this issue of failing to decode. but I didn't get why I am getting the issue.
The text was updated successfully, but these errors were encountered:
What is your question?
While running the asr_prep_json.py code in fairseq/examples/datasets I am getting exception of failed to decode the audio for few of .wav files. I don't understand why I am getting this error.I tried searching it in the existing issues and also on torchaudio but I still don't find kindly let me know how to fixthis.
Code
from future import absolute_import, division, print_function, unicode_literals
import argparse
import concurrent.futures
import json
import multiprocessing
import os
from collections import namedtuple
from itertools import chain
import sentencepiece as spm
from fairseq.data import Dictionary
MILLISECONDS_TO_SECONDS = 0.001
def process_sample(aud_path, lable, utt_id, sp, tgt_dict):
import torchaudio
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"--audio-dirs",
nargs="+",
default=["-"],
required=True,
help="input directories with audio files",
)
parser.add_argument(
"--labels",
required=True,
help="aggregated input labels with format per line",
type=argparse.FileType("r", encoding="UTF-8"),
)
parser.add_argument(
"--spm-model",
required=True,
help="sentencepiece model to use for encoding",
type=argparse.FileType("r", encoding="UTF-8"),
)
parser.add_argument(
"--dictionary",
required=True,
help="file to load fairseq dictionary from",
type=argparse.FileType("r", encoding="UTF-8"),
)
parser.add_argument("--audio-format", choices=["flac", "wav"], default="wav")
parser.add_argument(
"--output",
required=True,
type=argparse.FileType("w"),
help="path to save json output",
)
args = parser.parse_args()
if name == "main":
main()
What have you tried?
I tried printing the audios which is causing this issue of failing to decode. but I didn't get why I am getting the issue.
The text was updated successfully, but these errors were encountered: