From ff4306346eae4021c711df3fe23979e82e06e751 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 19 二月 2024 21:26:25 +0800
Subject: [PATCH] aishell example
---
examples/aishell/paraformer/run.sh | 7 ++++---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/examples/aishell/paraformer/run.sh b/examples/aishell/paraformer/run.sh
index 410751a..149f4d7 100755
--- a/examples/aishell/paraformer/run.sh
+++ b/examples/aishell/paraformer/run.sh
@@ -50,6 +50,7 @@
if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
echo "stage -1: Data Download"
+ mkdir -p ${raw_data}
local/download_and_untar.sh ${raw_data} ${data_url} data_aishell
local/download_and_untar.sh ${raw_data} ${data_url} resource_aishell
fi
@@ -76,9 +77,8 @@
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
echo "stage 1: Feature and CMVN Generation"
-# utils/compute_cmvn.sh --fbankdir ${feats_dir}/data/${train_set} --cmd "$train_cmd" --nj $nj --feats_dim ${feats_dim} --config_file "$config" --scale 1.0
python ../../../funasr/bin/compute_audio_cmvn.py \
- --config-path "${workspace}" \
+ --config-path "${workspace}/conf" \
--config-name "${config}" \
++train_data_set_list="${feats_dir}/data/${train_set}/audio_datasets.jsonl" \
++cmvn_file="${feats_dir}/data/${train_set}/cmvn.json" \
@@ -109,13 +109,14 @@
if [ ${stage} -le 4 ] && [ ${stop_stage} -ge 4 ]; then
echo "stage 4: ASR Training"
+ mkdir -p ${exp_dir}/exp/${model_dir}
log_file="${exp_dir}/exp/${model_dir}/train.log.txt"
echo "log_file: ${log_file}"
torchrun \
--nnodes 1 \
--nproc_per_node ${gpu_num} \
../../../funasr/bin/train.py \
- --config-path "${workspace}" \
+ --config-path "${workspace}/conf" \
--config-name "${config}" \
++train_data_set_list="${feats_dir}/data/${train_set}/audio_datasets.jsonl" \
++tokenizer_conf.token_list="${token_list}" \
--
Gitblit v1.9.1