Commit @41dd3c2c06e9cc0c6628415c8e33bd990194fca2 - yjyoon/whisper_streaming

Dominik Macháček 2024-11-23

Merge pull request #139 from dariopellegrino00/main

large-v3-turbo is now supported

@41dd3c2c06e9cc0c6628415c8e33bd990194fca2

c42dc8b

41dd3c2

README.md

--- README.md

+++ README.md


   --min-chunk-size MIN_CHUNK_SIZE
                         Minimum audio chunk size in seconds. It waits up to this time to do processing. If the processing takes shorter time, it waits, otherwise it processes the whole segment that was
                         received by this time.
-  --model {tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large}
+  --model {tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,large-v3-turbo}
                         Name size of the Whisper model to use (default: large-v2). The model is automatically downloaded from the model hub if not present in model cache dir.
   --model_cache_dir MODEL_CACHE_DIR
                         Overriding the default model cache dir where models downloaded from the hub are saved

c42dc8b

41dd3c2

whisper_online.py

--- whisper_online.py

+++ whisper_online.py


     parser: argparse.ArgumentParser object
     """
     parser.add_argument('--min-chunk-size', type=float, default=1.0, help='Minimum audio chunk size in seconds. It waits up to this time to do processing. If the processing takes shorter time, it waits, otherwise it processes the whole segment that was received by this time.')
-    parser.add_argument('--model', type=str, default='large-v2', choices="tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large".split(","),help="Name size of the Whisper model to use (default: large-v2). The model is automatically downloaded from the model hub if not present in model cache dir.")
+    parser.add_argument('--model', type=str, default='large-v2', choices="tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,large-v3-turbo".split(","),help="Name size of the Whisper model to use (default: large-v2). The model is automatically downloaded from the model hub if not present in model cache dir.")
     parser.add_argument('--model_cache_dir', type=str, default=None, help="Overriding the default model cache dir where models downloaded from the hub are saved")
     parser.add_argument('--model_dir', type=str, default=None, help="Dir where Whisper model.bin and other files are saved. This option overrides --model and --model_cache_dir parameter.")
     parser.add_argument('--lan', '--language', type=str, default='auto', help="Source language code, e.g. en,de,cs, or 'auto' for language detection.")

Add a comment

Open 0
Closed 0

List

...	...	@@ -94,7 +94,7 @@
94	94	--min-chunk-size MIN_CHUNK_SIZE
95	95	Minimum audio chunk size in seconds. It waits up to this time to do processing. If the processing takes shorter time, it waits, otherwise it processes the whole segment that was
96	96	received by this time.
97		- --model {tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large}
	97	+ --model {tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,large-v3-turbo}
98	98	Name size of the Whisper model to use (default: large-v2). The model is automatically downloaded from the model hub if not present in model cache dir.
99	99	--model_cache_dir MODEL_CACHE_DIR
100	100	Overriding the default model cache dir where models downloaded from the hub are saved

...	...	@@ -648,7 +648,7 @@
648	648	parser: argparse.ArgumentParser object
649	649	"""
650	650	parser.add_argument('--min-chunk-size', type=float, default=1.0, help='Minimum audio chunk size in seconds. It waits up to this time to do processing. If the processing takes shorter time, it waits, otherwise it processes the whole segment that was received by this time.')
651		- parser.add_argument('--model', type=str, default='large-v2', choices="tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large".split(","),help="Name size of the Whisper model to use (default: large-v2). The model is automatically downloaded from the model hub if not present in model cache dir.")
	651	+ parser.add_argument('--model', type=str, default='large-v2', choices="tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,large-v3-turbo".split(","),help="Name size of the Whisper model to use (default: large-v2). The model is automatically downloaded from the model hub if not present in model cache dir.")
652	652	parser.add_argument('--model_cache_dir', type=str, default=None, help="Overriding the default model cache dir where models downloaded from the hub are saved")
653	653	parser.add_argument('--model_dir', type=str, default=None, help="Dir where Whisper model.bin and other files are saved. This option overrides --model and --model_cache_dir parameter.")
654	654	parser.add_argument('--lan', '--language', type=str, default='auto', help="Source language code, e.g. en,de,cs, or 'auto' for language detection.")

Delete comment