feat: add hotwords argument to CLI for improved recognition of rare terms

whisperx/__main__.py

@@ -58,6 +58,7 @@ def cli():
     parser.add_argument("--suppress_numerals", action="store_true", help="whether to suppress numeric symbols and currency symbols during sampling, since wav2vec2 cannot align them correctly")
 
     parser.add_argument("--initial_prompt", type=str, default=None, help="optional text to provide as a prompt for the first window.")
+    parser.add_argument("--hotwords", type=str, default=None, help="hotwords/hint phrases to the model (e.g. \"WhisperX, PyAnnote, GPU\"); improves recognition of rare/technical terms")
     parser.add_argument("--condition_on_previous_text", type=str2bool, default=False, help="if True, provide the previous output of the model as a prompt for the next window; disabling may make the text inconsistent across windows, but the model becomes less prone to getting stuck in a failure loop")
     parser.add_argument("--fp16", type=str2bool, default=True, help="whether to perform inference in fp16; True by default")
 

whisperx/transcribe.py

@@ -106,6 +106,7 @@ def transcribe_task(args: dict, parser: argparse.ArgumentParser):
         "no_speech_threshold": args.pop("no_speech_threshold"),
         "condition_on_previous_text": False,
         "initial_prompt": args.pop("initial_prompt"),
+        "hotwords": args.pop("hotwords"),
         "suppress_tokens": [int(x) for x in args.pop("suppress_tokens").split(",")],
         "suppress_numerals": args.pop("suppress_numerals"),
     }