mirror of
https://github.com/k2-fsa/icefall.git
synced 2025-12-11 06:55:27 +00:00
915e8e399c
- Added CHiME-4 dataset integration in asr_datamodule.py - Added Hugging Face upload script - Added RIR augmentation - Added Self-Distillation Training
24 lines
608 B
Python
Executable File
24 lines
608 B
Python
Executable File
import os
|
|
|
|
import jsonlines
|
|
from tqdm import tqdm
|
|
|
|
dataset_parts = (
|
|
"dev-clean",
|
|
"train-clean-100",
|
|
"train-clean-360",
|
|
"train-other-500",
|
|
)
|
|
|
|
for part in dataset_parts:
|
|
with jsonlines.open(f"librispeech_cuts_{part}_raw.jsonl") as reader:
|
|
with jsonlines.open(f"librispeech_cuts_{part}.jsonl", mode="w") as writer:
|
|
for obj in tqdm(reader):
|
|
obj["custom"] = {"kmeans": obj["supervisions"][0]["custom"]["kmeans"]}
|
|
del obj["supervisions"][0]["custom"]
|
|
|
|
writer.write(obj)
|
|
|
|
os.system("rm *_raw.jsonl")
|
|
os.system("gzip *.jsonl")
|