making small model the default

README.md

@@ -37,17 +37,17 @@ choco install ffmpeg
 
 ## Command-line usage
 
-The following command will transcribe speech in audio files
+The following command will transcribe speech in audio files, using the `medium` model:
 
-    whisper audio.flac audio.mp3 audio.wav
+    whisper audio.flac audio.mp3 audio.wav --model medium
 
-The default setting works well for transcribing English. To transcribe an audio file containing non-English speech, you can specify the language using the `--language` option:
+The default setting (which selects the `small` model) works well for transcribing English. To transcribe an audio file containing non-English speech, you can specify the language using the `--language` option:
 
-    whisper ~/japanese.wav --language Japanese
+    whisper japanese.wav --language Japanese
 
 Adding `--task translate` will translate the speech into English:
 
-    whisper ~/japanese.wav --language Japanese --task translate
+    whisper japanese.wav --language Japanese --task translate
 
 Run the following to view all available transcription options:
 

whisper/transcribe.py

@@ -229,13 +229,13 @@ def cli():
 
     parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     parser.add_argument("audio", nargs="+", type=str, help="audio file(s) to transcribe")
-    parser.add_argument("--model", default="base", choices=available_models(), help="name of the Whisper model to use")
+    parser.add_argument("--model", default="small", choices=available_models(), help="name of the Whisper model to use")
     parser.add_argument("--device", default="cuda" if torch.cuda.is_available() else "cpu", help="device to use for PyTorch inference")
     parser.add_argument("--output_dir", "-o", type=str, default=".", help="directory to save the outputs")
     parser.add_argument("--verbose", type=str2bool, default=True, help="Whether to print out the progress and debug messages")
 
     parser.add_argument("--task", type=str, default="transcribe", choices=["transcribe", "translate"], help="whether to perform X->X speech recognition ('transcribe') or X->English translation ('translate')")
-    parser.add_argument("--language", type=str, default=None, choices=sorted(LANGUAGES.keys()) + sorted(TO_LANGUAGE_CODE.keys()), help="language spoken in the audio, specify None to perform language detection")
+    parser.add_argument("--language", type=str, default=None, choices=sorted(LANGUAGES.keys()) + sorted([k.title() for k in TO_LANGUAGE_CODE.keys()]), help="language spoken in the audio, specify None to perform language detection")
 
     parser.add_argument("--temperature", type=float, default=0, help="temperature to use for sampling")
     parser.add_argument("--best_of", type=optional_int, default=5, help="number of candidates when sampling with non-zero temperature")