From 8c5722de8ca55a13b74f580875ee1a35a24960ed Mon Sep 17 00:00:00 2001 From: Ewald Enzinger Date: Mon, 23 May 2022 17:37:35 +0200 Subject: [PATCH] [egs] Add prefix when reading manifests due to recent lhotse changes (#382) * [egs] Add prefix when reading manifests due to recent lhotse changes * Fix wenetspeech * Fix style issues --- egs/aishell/ASR/local/compute_fbank_aishell.py | 2 +- egs/aishell/ASR/local/process_aidatatang_200zh.py | 3 +-- egs/gigaspeech/ASR/local/compute_fbank_musan.py | 2 +- egs/librispeech/ASR/local/compute_fbank_librispeech.py | 2 +- egs/librispeech/ASR/local/compute_fbank_musan.py | 2 +- egs/spgispeech/ASR/local/compute_fbank_musan.py | 2 +- egs/tedlium3/ASR/local/compute_fbank_tedlium.py | 2 +- egs/timit/ASR/local/compute_fbank_timit.py | 2 +- egs/wenetspeech/ASR/local/preprocess_wenetspeech.py | 1 + 9 files changed, 9 insertions(+), 9 deletions(-) diff --git a/egs/aishell/ASR/local/compute_fbank_aishell.py b/egs/aishell/ASR/local/compute_fbank_aishell.py index b3b9e7681..70dee81d8 100755 --- a/egs/aishell/ASR/local/compute_fbank_aishell.py +++ b/egs/aishell/ASR/local/compute_fbank_aishell.py @@ -53,7 +53,7 @@ def compute_fbank_aishell(num_mel_bins: int = 80): "test", ) manifests = read_manifests_if_cached( - dataset_parts=dataset_parts, output_dir=src_dir + prefix="aishell", dataset_parts=dataset_parts, output_dir=src_dir ) assert manifests is not None diff --git a/egs/aishell/ASR/local/process_aidatatang_200zh.py b/egs/aishell/ASR/local/process_aidatatang_200zh.py index 2c6951d42..ac2b86927 100755 --- a/egs/aishell/ASR/local/process_aidatatang_200zh.py +++ b/egs/aishell/ASR/local/process_aidatatang_200zh.py @@ -35,8 +35,7 @@ def preprocess_aidatatang_200zh(): logging.info("Loading manifest") manifests = read_manifests_if_cached( - dataset_parts=dataset_parts, - output_dir=src_dir, + dataset_parts=dataset_parts, output_dir=src_dir, prefix="aidatatang" ) assert len(manifests) > 0 diff --git a/egs/gigaspeech/ASR/local/compute_fbank_musan.py b/egs/gigaspeech/ASR/local/compute_fbank_musan.py index 219f4bdca..562872993 100755 --- a/egs/gigaspeech/ASR/local/compute_fbank_musan.py +++ b/egs/gigaspeech/ASR/local/compute_fbank_musan.py @@ -53,7 +53,7 @@ def compute_fbank_musan(): ) manifests = read_manifests_if_cached( - dataset_parts=dataset_parts, output_dir=src_dir + prefix="musan", dataset_parts=dataset_parts, output_dir=src_dir ) assert manifests is not None diff --git a/egs/librispeech/ASR/local/compute_fbank_librispeech.py b/egs/librispeech/ASR/local/compute_fbank_librispeech.py index 5c33ff8be..92f4f6ab7 100755 --- a/egs/librispeech/ASR/local/compute_fbank_librispeech.py +++ b/egs/librispeech/ASR/local/compute_fbank_librispeech.py @@ -57,7 +57,7 @@ def compute_fbank_librispeech(): "train-other-500", ) manifests = read_manifests_if_cached( - dataset_parts=dataset_parts, output_dir=src_dir + prefix="librispeech", dataset_parts=dataset_parts, output_dir=src_dir ) assert manifests is not None diff --git a/egs/librispeech/ASR/local/compute_fbank_musan.py b/egs/librispeech/ASR/local/compute_fbank_musan.py index f5911746b..368bea4e8 100755 --- a/egs/librispeech/ASR/local/compute_fbank_musan.py +++ b/egs/librispeech/ASR/local/compute_fbank_musan.py @@ -53,7 +53,7 @@ def compute_fbank_musan(): "noise", ) manifests = read_manifests_if_cached( - dataset_parts=dataset_parts, output_dir=src_dir + prefix="musan", dataset_parts=dataset_parts, output_dir=src_dir ) assert manifests is not None diff --git a/egs/spgispeech/ASR/local/compute_fbank_musan.py b/egs/spgispeech/ASR/local/compute_fbank_musan.py index 57805a756..b88286c41 100755 --- a/egs/spgispeech/ASR/local/compute_fbank_musan.py +++ b/egs/spgispeech/ASR/local/compute_fbank_musan.py @@ -65,7 +65,7 @@ def compute_fbank_musan(): "noise", ) manifests = read_manifests_if_cached( - dataset_parts=dataset_parts, output_dir=src_dir + prefix="musan", dataset_parts=dataset_parts, output_dir=src_dir ) assert manifests is not None diff --git a/egs/tedlium3/ASR/local/compute_fbank_tedlium.py b/egs/tedlium3/ASR/local/compute_fbank_tedlium.py index b3ae00230..14200f34f 100755 --- a/egs/tedlium3/ASR/local/compute_fbank_tedlium.py +++ b/egs/tedlium3/ASR/local/compute_fbank_tedlium.py @@ -53,7 +53,7 @@ def compute_fbank_tedlium(): ) manifests = read_manifests_if_cached( - dataset_parts=dataset_parts, output_dir=src_dir + prefix="tedlium", dataset_parts=dataset_parts, output_dir=src_dir ) assert manifests is not None diff --git a/egs/timit/ASR/local/compute_fbank_timit.py b/egs/timit/ASR/local/compute_fbank_timit.py index 70be7051c..8e3cbac4e 100644 --- a/egs/timit/ASR/local/compute_fbank_timit.py +++ b/egs/timit/ASR/local/compute_fbank_timit.py @@ -54,7 +54,7 @@ def compute_fbank_timit(): "TEST", ) manifests = read_manifests_if_cached( - dataset_parts=dataset_parts, output_dir=src_dir + prefix="timit", dataset_parts=dataset_parts, output_dir=src_dir ) assert manifests is not None diff --git a/egs/wenetspeech/ASR/local/preprocess_wenetspeech.py b/egs/wenetspeech/ASR/local/preprocess_wenetspeech.py index 6afc56dda..64733eb15 100755 --- a/egs/wenetspeech/ASR/local/preprocess_wenetspeech.py +++ b/egs/wenetspeech/ASR/local/preprocess_wenetspeech.py @@ -62,6 +62,7 @@ def preprocess_wenet_speech(): dataset_parts=dataset_parts, output_dir=src_dir, suffix="jsonl.gz", + prefix="wenetspeech", ) assert manifests is not None