Add transducer conformer configuration to commonvoice recipe #5503
Conversation
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
- Add a transducer conformer training configuration `train_asr_transducer_conformer5.yaml`. - Added a decoding configuration for transducer in `decode_transducer.yaml`. - The model has been trained and tested on NVIDIA A100 GPU.
Codecov Report
@@ Coverage Diff @@
## master #5503 +/- ##
=======================================
Coverage 75.40% 75.40%
=======================================
Files 709 709
Lines 65361 65361
=======================================
+ Hits 49287 49288 +1
+ Misses 16074 16073 -1
Flags with carried forward coverage won't be shown. Click here to find out more. see 1 file with indirect coverage changes 📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
sw005320
added
Recipe
ASR
|
Thank! |
|
Sure! I added the results of both the Conformer5 and the Transducer-Conformer5 to the README. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What?
This PR introduces a new transducer conformer configuration for the CommonVoice recipe:
train_asr_conformer5.yamlprovided).We tested the model in an NVIDIA A100 GPU, but smaller GPUs can probably be used.
Scores
We have tested the model with the Basque language (
eu) only.Common Voice 14 test set:
train_asr_conformer5.yamltrain_asr_transducer_conformer5.yamlAhoMyTTS (a private difficult dataset):
train_asr_conformer5.yamltrain_asr_transducer_conformer5.yamlWhy?
The scores are similar to the provided Conformer5 configuration. But I thought you may be interested in including it, offering users an alternative method to train ASR models on the CommonVoice dataset.
The model: https://huggingface.co/espnet/zuazo_commonvoice_asr_train_asr_transducer_conformer5_raw_eu_bpe150_sp
Feedback and suggestions are welcome!