demos: update example (#3852)

Author: Wovchena

demos/sound_classification_demo/python/README.md

@@ -67,6 +67,8 @@ You can use the following command to do inference on GPU with a pre-trained soun
 python3 sound_classification_demo.py -i <path_to_wav>/input_audio.wav -m <path_to_model>/aclnet.xml -d GPU --sample_rate 16000
 ```
 
+An example audio file can be taken from https://storage.openvinotoolkit.org/models_contrib/speech/2021.2/librispeech_s5/how_are_you_doing_today.wav.
+
 ## Demo Output
 
 The demo uses console to display the predictions. It shows classification of each clip and total prediction of whole audio.

demos/speech_recognition_deepspeech_demo/python/README.md

@@ -128,7 +128,7 @@ To run in *simulated real-time mode* add command-line option `--realtime`.
 > **NOTE**: Only 16-bit, 16 kHz, mono-channel WAVE audio files are supported.
 
 Optional (but highly recommended) language model files, `deepspeech-0.8.2-models.kenlm` or `lm.binary` are part of corresponding model downloaded content and will be located in the Model Downloader output folder after model downloading and conversion.
-An example audio file can be taken from OpenVINO [test data](https://storage.openvinotoolkit.org/data/test_data/) folder.
+An example audio file can be taken from https://storage.openvinotoolkit.org/models_contrib/speech/2021.2/librispeech_s5/how_are_you_doing_today.wav.
 
 ## Demo Output
 

demos/speech_recognition_quartznet_demo/python/README.md

@@ -57,7 +57,7 @@ python3 speech_recognition_quartznet_demo.py -m quartznet-15x5-en.xml -i audio.w
 
 > **NOTE**: Only 16-bit, 16 kHz, mono-channel WAVE audio files are supported.
 
-An example audio file can be taken from OpenVINO [test data](https://storage.openvinotoolkit.org/data/test_data/) folder.
+An example audio file can be taken from https://storage.openvinotoolkit.org/models_contrib/speech/2021.2/librispeech_s5/how_are_you_doing_today.wav.
 
 ## Demo Output
 

demos/speech_recognition_wav2vec_demo/python/README.md

@@ -58,7 +58,7 @@ python3 speech_recognition_wav2vec_demo.py -m wav2vec2-base.xml -i audio.wav
 
 > **NOTE**: Only 16-bit, 16 kHz, mono-channel WAVE audio files are supported.
 
-An example audio file can be taken from OpenVINO [test data](https://storage.openvinotoolkit.org/data/test_data/) folder.
+An example audio file can be taken from https://storage.openvinotoolkit.org/models_contrib/speech/2021.2/librispeech_s5/how_are_you_doing_today.wav.
 
 ## Demo Output