mirror of
https://github.com/m-bain/whisperX.git
synced 2025-07-01 18:17:27 -04:00
init commit
This commit is contained in:
1
whisperx/assets/multilingual/added_tokens.json
Normal file
1
whisperx/assets/multilingual/added_tokens.json
Normal file
@ -0,0 +1 @@
|
||||
{"<|endoftext|>": 50257}
|
50000
whisperx/assets/multilingual/merges.txt
Normal file
50000
whisperx/assets/multilingual/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
1
whisperx/assets/multilingual/special_tokens_map.json
Normal file
1
whisperx/assets/multilingual/special_tokens_map.json
Normal file
@ -0,0 +1 @@
|
||||
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
1
whisperx/assets/multilingual/tokenizer_config.json
Normal file
1
whisperx/assets/multilingual/tokenizer_config.json
Normal file
@ -0,0 +1 @@
|
||||
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "multilingual", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
|
1
whisperx/assets/multilingual/vocab.json
Normal file
1
whisperx/assets/multilingual/vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user