-
Notifications
You must be signed in to change notification settings - Fork 1.9k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
7 changed files
with
100,573 additions
and
7 deletions.
There are no files selected for viewing
6 changes: 5 additions & 1 deletion
6
paddlespeech/s2t/models/whisper/assets/gpt2/special_tokens_map.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1 +1,5 @@ | ||
| {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"} | ||
| { | ||
| "bos_token": "<|endoftext|>", | ||
| "eos_token": "<|endoftext|>", | ||
| "unk_token": "<|endoftext|>" | ||
| } |
11 changes: 10 additions & 1 deletion
11
paddlespeech/s2t/models/whisper/assets/gpt2/tokenizer_config.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1 +1,10 @@ | ||
| {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"} | ||
| { | ||
| "unk_token": "<|endoftext|>", | ||
| "bos_token": "<|endoftext|>", | ||
| "eos_token": "<|endoftext|>", | ||
| "add_prefix_space": false, | ||
| "model_max_length": 1024, | ||
| "special_tokens_map_file": null, | ||
| "name_or_path": "gpt2", | ||
| "tokenizer_class": "GPT2Tokenizer" | ||
| } |
50,260 changes: 50,259 additions & 1 deletion
50,260
paddlespeech/s2t/models/whisper/assets/gpt2/vocab.json
Large diffs are not rendered by default.
Oops, something went wrong.
4 changes: 3 additions & 1 deletion
4
paddlespeech/s2t/models/whisper/assets/multilingual/added_tokens.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1 +1,3 @@ | ||
| {"<|endoftext|>": 50257} | ||
| { | ||
| "<|endoftext|>": 50257 | ||
| } |
6 changes: 5 additions & 1 deletion
6
paddlespeech/s2t/models/whisper/assets/multilingual/special_tokens_map.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1 +1,5 @@ | ||
| {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"} | ||
| { | ||
| "bos_token": "<|endoftext|>", | ||
| "eos_token": "<|endoftext|>", | ||
| "unk_token": "<|endoftext|>" | ||
| } |
33 changes: 32 additions & 1 deletion
33
paddlespeech/s2t/models/whisper/assets/multilingual/tokenizer_config.json
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1 +1,32 @@ | ||
| {"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"} | ||
| { | ||
| "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" | ||
| } |
50,260 changes: 50,259 additions & 1 deletion
50,260
paddlespeech/s2t/models/whisper/assets/multilingual/vocab.json
Large diffs are not rendered by default.
Oops, something went wrong.