From 362a6de3c850079ed2ae6f94181f2a51c0596527 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 20 二月 2024 15:22:13 +0800
Subject: [PATCH] update
---
examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml | 9 ++++++---
examples/aishell/conformer/run.sh | 11 ++++++++---
examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml | 9 ++++++---
examples/aishell/transformer/conf/transformer_12e_6d_2048_256.yaml | 11 +++++++----
examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml | 9 ++++++---
5 files changed, 33 insertions(+), 16 deletions(-)
diff --git a/examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml b/examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml
index 09b1e0f..d6caf5d 100644
--- a/examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml
+++ b/examples/aishell/branchformer/conf/branchformer_12e_6d_2048_256.yaml
@@ -94,13 +94,16 @@
dataset: AudioDataset
dataset_conf:
index_ds: IndexDSJsonl
- batch_sampler: DynamicBatchLocalShuffleSampler
+ batch_sampler: RankFullLocalShuffleBatchSampler
batch_type: example # example or length
- batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
+ batch_size: 32 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
- buffer_size: 500
+ buffer_size: 1024
shuffle: True
num_workers: 4
+ preprocessor_speech: SpeechPreprocessSpeedPerturb
+ preprocessor_speech_conf:
+ speed_perturb: [0.9, 1.0, 1.1]
tokenizer: CharTokenizer
tokenizer_conf:
diff --git a/examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml b/examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml
index 1197e87..8909b15 100644
--- a/examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml
+++ b/examples/aishell/conformer/conf/conformer_12e_6d_2048_256.yaml
@@ -94,13 +94,16 @@
dataset: AudioDataset
dataset_conf:
index_ds: IndexDSJsonl
- batch_sampler: DynamicBatchLocalShuffleSampler
+ batch_sampler: RankFullLocalShuffleBatchSampler
batch_type: example # example or length
- batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
+ batch_size: 32 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
- buffer_size: 500
+ buffer_size: 1024
shuffle: True
num_workers: 4
+ preprocessor_speech: SpeechPreprocessSpeedPerturb
+ preprocessor_speech_conf:
+ speed_perturb: [0.9, 1.0, 1.1]
tokenizer: CharTokenizer
tokenizer_conf:
diff --git a/examples/aishell/conformer/run.sh b/examples/aishell/conformer/run.sh
index 28e6f90..947cc02 100755
--- a/examples/aishell/conformer/run.sh
+++ b/examples/aishell/conformer/run.sh
@@ -109,9 +109,14 @@
echo "log_file: ${log_file}"
gpu_num=$(echo CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
- torchrun \
- --nnodes 1 \
- --nproc_per_node ${gpu_num} \
+# torchrun \
+# --nnodes 1 \
+# --nproc_per_node ${gpu_num}
+ cmd="python"
+ if [ ${gpu_num} -gt 1 ];then
+ cmd="torchrun --nnodes 1 --nproc_per_node ${gpu_num}"
+ fi
+ ${cmd} \
../../../funasr/bin/train.py \
--config-path "${workspace}/conf" \
--config-name "${config}" \
diff --git a/examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml b/examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml
index dea580e..e6cc1e6 100644
--- a/examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml
+++ b/examples/aishell/e_branchformer/conf/e_branchformer_12e_6d_2048_256.yaml
@@ -94,13 +94,16 @@
dataset: AudioDataset
dataset_conf:
index_ds: IndexDSJsonl
- batch_sampler: DynamicBatchLocalShuffleSampler
+ batch_sampler: RankFullLocalShuffleBatchSampler
batch_type: example # example or length
- batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
+ batch_size: 32 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
- buffer_size: 500
+ buffer_size: 1024
shuffle: True
num_workers: 4
+ preprocessor_speech: SpeechPreprocessSpeedPerturb
+ preprocessor_speech_conf:
+ speed_perturb: [0.9, 1.0, 1.1]
tokenizer: CharTokenizer
tokenizer_conf:
diff --git a/examples/aishell/transformer/transformer_12e_6d_2048_256.yaml b/examples/aishell/transformer/conf/transformer_12e_6d_2048_256.yaml
similarity index 86%
rename from examples/aishell/transformer/transformer_12e_6d_2048_256.yaml
rename to examples/aishell/transformer/conf/transformer_12e_6d_2048_256.yaml
index 87814dc..24a6390 100644
--- a/examples/aishell/transformer/transformer_12e_6d_2048_256.yaml
+++ b/examples/aishell/transformer/conf/transformer_12e_6d_2048_256.yaml
@@ -88,13 +88,16 @@
dataset: AudioDataset
dataset_conf:
index_ds: IndexDSJsonl
- batch_sampler: DynamicBatchLocalShuffleSampler
+ batch_sampler: RankFullLocalShuffleBatchSampler
batch_type: example # example or length
- batch_size: 1 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
+ batch_size: 32 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
- buffer_size: 500
+ buffer_size: 1024
shuffle: True
- num_workers: 0
+ num_workers: 4
+ preprocessor_speech: SpeechPreprocessSpeedPerturb
+ preprocessor_speech_conf:
+ speed_perturb: [0.9, 1.0, 1.1]
tokenizer: CharTokenizer
tokenizer_conf:
--
Gitblit v1.9.1