This repository was archived by the owner on Jul 7, 2023. It is now read-only.
Word Error Rate for Speech Recognition #1242
Merged
Conversation
This file contains hidden or 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
|
Thanks @stefan-falk ! |
tensorflow-copybara
pushed a commit
that referenced
this pull request
Nov 29, 2018
PiperOrigin-RevId: 223252032
|
@afrozenator You're welcome. Thanks for accepting :) |
theorm
added a commit
to theorm/tensor2tensor
that referenced
this pull request
Dec 4, 2018
* master: (300 commits) Allow vgg_ckpt_dir as a decode_hparam and make it None by default. flags.py -> (utils/flags.py) Move nfg to models/video for external collaboration. Move nfg to models/video for external collaboration. Undefined name: xrange() was removed in Python 3 (tensorflow#1258) internal merge of PR tensorflow#1257 Fix universal transformer decoding (tensorflow#1257) Let weights_multi_problem_all support tensor taskid Delete unused only_last from dataset. The functionality was buggy to Internal change Add En-Ro translation, reserve ids for extra tasks in TPU adafactor multi-Transformer. adding 256*256 imagenet class to t2t.problems. internal merge of PR tensorflow#1256 Differentiate summaries for train and eval. (tensorflow#1256) internal merge of PR tensorflow#1242 Word Error Rate for Speech Recognition (tensorflow#1242) internal merge of PR tensorflow#1253 internal merge of PR tensorflow#1247 add problems, conll2002_es_ner and conll2002_nl_ner (tensorflow#1253) Fix MRPC link (tensorflow#1247) ...
kpe
pushed a commit
to kpe/tensor2tensor
that referenced
this pull request
Mar 2, 2019
kpe
pushed a commit
to kpe/tensor2tensor
that referenced
this pull request
Mar 2, 2019
PiperOrigin-RevId: 223252032
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Proposing an additional metric: Word Error Rate
Changes:
word_error_rateintensor2tensor/utils/metrics.pytensor2tensor/utils/metrics_test.pySpeechRecognitionProblemtensor2tensor/data_generators/speech_recognition.py