Fix typos

.github/scripts/baker_zh/TTS/run-matcha.sh

@@ -92,7 +92,7 @@ function export_onnx() {
   ls -lh *.onnx
 
   if false; then
-    # THe CI machine does not have enough memory to run it
+    # The CI machine does not have enough memory to run it
     #
     curl -SL -O https://github.com/csukuangfj/models/raw/refs/heads/master/hifigan/generator_v1
     curl -SL -O https://github.com/csukuangfj/models/raw/refs/heads/master/hifigan/generator_v2

.github/scripts/ljspeech/TTS/run-matcha.sh

@@ -90,7 +90,7 @@ function export_onnx() {
   ls -lh *.onnx
 
   if false; then
-    # THe CI machine does not have enough memory to run it
+    # The CI machine does not have enough memory to run it
     #
     curl -SL -O https://github.com/csukuangfj/models/raw/refs/heads/master/hifigan/generator_v1
     curl -SL -O https://github.com/csukuangfj/models/raw/refs/heads/master/hifigan/generator_v2

.github/workflows/baker_zh.yml

@@ -12,7 +12,7 @@ on:
   workflow_dispatch:
 
 concurrency:
-  group: ljspeech-${{ github.ref }}
+  group: baker-zh-${{ github.ref }}
   cancel-in-progress: true
 
 jobs:

egs/baker_zh/TTS/.gitignore

@@ -1,4 +1,5 @@
 path.sh
+*.onnx
 *.wav
 generator_v1
 generator_v2

egs/baker_zh/TTS/README.md

@@ -3,7 +3,11 @@
 It is for the dataset from
 https://en.data-baker.com/datasets/freeDatasets/
 
-The dataset contains 10000 Chinese sentences of a native Chinese female speaker.
+The dataset contains 10000 Chinese sentences of a native Chinese female speaker,
+which is about 12 hours.
+
+
+**Note**: The dataset is for non-commercial use only.
 
 
 # matcha
@@ -28,7 +32,7 @@ python3 ./matcha/train.py \
 To inference, use:
 
 ```bash
-# Download Hifigan vocoder. We use Hifigan v1 below. You can select from v1, v2, or v3
+# Download Hifigan vocoder. We use Hifigan v2 below. You can select from v1, v2, or v3
 
 wget https://github.com/csukuangfj/models/raw/refs/heads/master/hifigan/generator_v2
 
@@ -70,7 +74,7 @@ python3 ./matcha/export_onnx.py \
   --cmvn ./data/fbank/cmvn.json
 ```
 
-The above command generate the following files:
+The above command generates the following files:
 ```
 -rw-r--r-- 1 kuangfangjun root 72M Dec 27 18:53 model-steps-2.onnx
 -rw-r--r-- 1 kuangfangjun root 73M Dec 27 18:54 model-steps-3.onnx

egs/baker_zh/TTS/matcha/export_onnx.py

@@ -191,7 +191,7 @@ def main():
             "model_author": "icefall",
             "maintainer": "k2-fsa",
             "dataset": "baker-zh",
-            "use_eos_bos": 1,
+            "use_eos_bos": 0,
             "dataset_url": "https://www.data-baker.com/open_source.html",
             "dataset_comment": "The dataset is for non-commercial use only.",
             "num_ode_steps": num_steps,

egs/ljspeech/TTS/README.md

@@ -166,7 +166,7 @@ To export the checkpoint to onnx:
   --tokens ./data/tokens.txt
 ```
 
-The above command generate the following files:
+The above command generates the following files:
 
   - model-steps-2.onnx
   - model-steps-3.onnx