Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update config for AED models #8294

Merged
merged 1 commit into from
Jan 31, 2024
Merged

Update config for AED models #8294

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 13 additions & 2 deletions examples/asr/conf/speech_multitask/fast-conformer_aed.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,8 +74,19 @@ model:
# recommend small vocab size of 128 or 256 when using 4x sub-sampling
# you may find more detail on how to train a tokenizer at: /scripts/tokenizers/process_asr_text_tokenizer.py
tokenizer:
dir: ??? # path to directory which contains either tokenizer.model (bpe) or vocab.txt (wpe)
type: bpe # Can be either bpe (SentencePiece tokenizer) or wpe (WordPiece tokenizer)
dir: null # Null for aggregate tokenizers
type: agg # Can be either bpe (SentencePiece tokenizer) or wpe (WordPiece tokenizer) or `agg` for aggregate tokenizers
langs:
spl_tokens: # special tokens model
dir: ???
type: bpe
en: # English tokenizer (example, replace with whichever language you would like)
dir: ???
type: bpe

custom_tokenizer:
_target_: nemo.collections.common.tokenizers.canary_tokenizer.CanaryTokenizer # Can be replaced with other tokenizer for different prompt formats
tokenizers: null # Filled at runtime by all the tokenizers inside the aggregate tokenizer

# Audio Preprocessor
preprocessor:
Expand Down
Loading