Update asr.py

asr.py

@@ -20,50 +20,52 @@ processor = AutoProcessor.from_pretrained(MODEL_ID)
 model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
 
 
-lm_decoding_config = {}
-lm_decoding_configfile = hf_hub_download(
-    repo_id="facebook/mms-cclms",
-    filename="decoding_config.json",
-    subfolder="mms-1b-all",
-)
-
-with open(lm_decoding_configfile) as f:
-    lm_decoding_config = json.loads(f.read())
-
-# allow language model decoding for "eng"
-
-decoding_config = lm_decoding_config["eng"]
-
-lm_file = hf_hub_download(
-    repo_id="facebook/mms-cclms",
-    filename=decoding_config["lmfile"].rsplit("/", 1)[1],
-    subfolder=decoding_config["lmfile"].rsplit("/", 1)[0],
-)
-token_file = hf_hub_download(
-    repo_id="facebook/mms-cclms",
-    filename=decoding_config["tokensfile"].rsplit("/", 1)[1],
-    subfolder=decoding_config["tokensfile"].rsplit("/", 1)[0],
-)
-lexicon_file = None
-if decoding_config["lexiconfile"] is not None:
-    lexicon_file = hf_hub_download(
-        repo_id="facebook/mms-cclms",
-        filename=decoding_config["lexiconfile"].rsplit("/", 1)[1],
-        subfolder=decoding_config["lexiconfile"].rsplit("/", 1)[0],
-    )
+# lm_decoding_config = {}
+# lm_decoding_configfile = hf_hub_download(
+#     repo_id="facebook/mms-cclms",
+#     filename="decoding_config.json",
+#     subfolder="mms-1b-all",
+# )
+
+# with open(lm_decoding_configfile) as f:
+#     lm_decoding_config = json.loads(f.read())
+
+# # allow language model decoding for "eng"
+
+# decoding_config = lm_decoding_config["eng"]
+
+# lm_file = hf_hub_download(
+#     repo_id="facebook/mms-cclms",
+#     filename=decoding_config["lmfile"].rsplit("/", 1)[1],
+#     subfolder=decoding_config["lmfile"].rsplit("/", 1)[0],
+# )
+# token_file = hf_hub_download(
+#     repo_id="facebook/mms-cclms",
+#     filename=decoding_config["tokensfile"].rsplit("/", 1)[1],
+#     subfolder=decoding_config["tokensfile"].rsplit("/", 1)[0],
+# )
+# lexicon_file = None
+# if decoding_config["lexiconfile"] is not None:
+#     lexicon_file = hf_hub_download(
+#         repo_id="facebook/mms-cclms",
+#         filename=decoding_config["lexiconfile"].rsplit("/", 1)[1],
+#         subfolder=decoding_config["lexiconfile"].rsplit("/", 1)[0],
+#     )
+
+beam_search_decoder = None     
+# beam_search_decoder = ctc_decoder(
+#     lexicon=lexicon_file,
+#     tokens=token_file,
+#     lm=lm_file,
+#     nbest=1,
+#     beam_size=500,
+#     beam_size_token=50,
+#     lm_weight=float(decoding_config["lmweight"]),
+#     word_score=float(decoding_config["wordscore"]),
+#     sil_score=float(decoding_config["silweight"]),
+#     blank_token="<s>",
+# )
 
-beam_search_decoder = ctc_decoder(
-    lexicon=lexicon_file,
-    tokens=token_file,
-    lm=lm_file,
-    nbest=1,
-    beam_size=500,
-    beam_size_token=50,
-    lm_weight=float(decoding_config["lmweight"]),
-    word_score=float(decoding_config["wordscore"]),
-    sil_score=float(decoding_config["silweight"]),
-    blank_token="<s>",
-)
 
 def transcribe(
     audio_source=None, microphone=None, file_upload=None, lang="eng (English)"