Update example code to use latest ReazonSpeech API

Signed-off-by: Fujimoto Seiji <fujimoto@ceptord.net>

README.md

@@ -26,21 +26,17 @@ The general architecture is the same as [reazonspeech-espnet-v1](https://hugging
 
 ## Usage
 
-We provide `transcribe()` function that is suitable to use with this
-model.
+We recommend to use this model through our
+[reazonspeech](https://github.com/reazon-research/reazonspeech)
+library.
 
 ```
-from espnet2.bin.asr_inference import Speech2Text
-from reazonspeech.espnet.asr import transcribe
+from reazonspeech.espnet.asr import load_model, transcribe, audio_from_path
 
-speech2text = Speech2Text(
-    "exp/asr_train_asr_conformer_raw_jp_char/config.yaml",
-    "exp/asr_train_asr_conformer_raw_jp_char/valid.acc.ave_10best.pth",
-    device="cuda"
-)
-
-for cap in transcribe("speech.wav", speech2text):
-    print(cap)
+audio = audio_from_path("speech.wav")
+model = load_model()
+ret = transcribe(model, audio)
+print(ret.text)
 ```
 
 ## License