Play generated audio as it is generating. (#457)

python-api-examples/offline-tts.py

@@ -6,29 +6,30 @@
 This file demonstrates how to use sherpa-onnx Python API to generate audio
 from text, i.e., text-to-speech.
 
+
+Different from ./offline-tts-play.py, this file does not play back the
+generated audio.
+
 Usage:
 
-1. Download a model
+Example (1/2)
 
-wget https://huggingface.co/csukuangfj/vits-ljs/resolve/main/vits-ljs.onnx
-wget https://huggingface.co/csukuangfj/vits-ljs/resolve/main/lexicon.txt
-wget https://huggingface.co/csukuangfj/vits-ljs/resolve/main/tokens.txt
+wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2
+tar xf vits-piper-en_US-amy-low.tar.bz2
 
 python3 ./python-api-examples/offline-tts.py \
-  --vits-model=./vits-ljs.onnx \
-  --vits-lexicon=./lexicon.txt \
-  --vits-tokens=./tokens.txt \
-  --output-filename=./generated.wav \
-  'liliana, the most beautiful and lovely assistant of our team!'
+ --vits-model=./vits-piper-en_US-amy-low/en_US-amy-low.onnx \
+ --vits-tokens=./vits-piper-en_US-amy-low/tokens.txt \
+ --vits-data-dir=./vits-piper-en_US-amy-low/espeak-ng-data \
+ --output-filename=./generated.wav \
+ "Today as always, men fall into two groups: slaves and free men. Whoever does not have two-thirds of his day for himself, is a slave, whatever he may be: a statesman, a businessman, an official, or a scholar."
 
-2. Download a model
+Example (2/2)
 
-wget https://huggingface.co/csukuangfj/vits-zh-aishell3/resolve/main/vits-aishell3.onnx
-wget https://huggingface.co/csukuangfj/vits-zh-aishell3/resolve/main/lexicon.txt
-wget https://huggingface.co/csukuangfj/vits-zh-aishell3/resolve/main/tokens.txt
-wget https://huggingface.co/csukuangfj/vits-zh-aishell3/resolve/main/rule.fst
+wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-zh-aishell3.tar.bz2
+tar xvf vits-zh-aishell3.tar.bz2
 
-python3 ./python-api-examples/offline-tts.py 
+python3 ./python-api-examples/offline-tts.py \
  --vits-model=./vits-aishell3.onnx \
  --vits-lexicon=./lexicon.txt \
  --vits-tokens=./tokens.txt \
@@ -37,9 +38,13 @@ python3 ./python-api-examples/offline-tts.py
  --output-filename=./liubei-21.wav \
  "勿以恶小而为之，勿以善小而不为。惟贤惟德，能服于人。122334"
 
+You can find more models at
+https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
+
 Please see
 https://k2-fsa.github.io/sherpa/onnx/tts/index.html
 for details.
+
 """
 
 import argparse