Create app.py

app.py

@@ -0,0 +1,48 @@
+import time
+import torch
+import string
+from espnet_model_zoo.downloader import ModelDownloader
+from espnet2.bin.asr_inference import Speech2Text
+
+
+import soundfile
+import librosa.display
+import matplotlib.pyplot as plt
+import gradio as gr
+
+
+
+def inference(audio)
+  speech, rate = soundfile.read(audio.name)
+  assert rate == fs, "mismatch in sampling rate"
+  nbests = speech2text(speech)
+  text, *_ = nbests[0]
+
+  print(f"Input Speech: {file_name}")
+  display(Audio(speech, rate=rate))
+  librosa.display.waveplot(speech, sr=rate)
+  plt.show()
+  print(f"ASR hypothesis: {text_normalizer(text)}")
+  print("*" * 50)
+
+
+d = ModelDownloader()
+# It may takes a while to download and build models
+speech2text = Speech2Text(
+    **d.download_and_unpack(tag),
+    device="cpu",
+    minlenratio=0.0,
+    maxlenratio=0.0,
+    ctc_weight=0.3,
+    beam_size=10,
+    batch_size=0,
+    nbest=1
+)
+
+def text_normalizer(text):
+    text = text.upper()
+    return text.translate(str.maketrans('', '', string.punctuation))
+    
+lang = 'multilingual'
+fs = 16000 
+tag = 'ftshijt/open_li52_asr_train_asr_raw_bpe7000_valid.acc.ave_10best'