From 250620694cece2821b37cc9ef7b1d5a74ce3c7f3 Mon Sep 17 00:00:00 2001 From: Dongji Gao Date: Mon, 18 Sep 2023 23:26:59 -0400 Subject: [PATCH 1/3] Update README.md --- egs/librispeech/WSASR/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/egs/librispeech/WSASR/README.md b/egs/librispeech/WSASR/README.md index ea0eaa6d3..471243464 100644 --- a/egs/librispeech/WSASR/README.md +++ b/egs/librispeech/WSASR/README.md @@ -124,7 +124,7 @@ The bypass arc deals with substitution and insertion errors, while the self-loop ### Decoding ``` export CUDA_VISIBLE_DEVICES="0" -python conformer_ctc2/decode.py \ +./conformer_ctc2/decode.py \ --exp-dir "${exp_dir}" \ --lang-dir "${otc_lang_dir}" \ --lm-dir "${lm_dir}" \ From 74a4005f9fd39668a6c1617388f6f187e4835dee Mon Sep 17 00:00:00 2001 From: Dongji Gao Date: Tue, 19 Sep 2023 10:36:44 -0400 Subject: [PATCH 2/3] Add BTC paper link --- egs/librispeech/WSASR/README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/egs/librispeech/WSASR/README.md b/egs/librispeech/WSASR/README.md index 471243464..adcf201c3 100644 --- a/egs/librispeech/WSASR/README.md +++ b/egs/librispeech/WSASR/README.md @@ -1,7 +1,7 @@ # Introduction This is a weakly supervised ASR recipe for the LibriSpeech (clean 100 hours) dataset. We train a -conformer model using Bypass Temporal Classification (BTC)/Omni-temporal Classification (OTC) with transcripts with synthetic errors. In this README, we will describe +conformer model using [Bypass Temporal Classification](https://arxiv.org/pdf/2306.01031.pdf) (BTC)/Omni-temporal Classification (OTC) with transcripts with synthetic errors. In this README, we will describe the task and the BTC/OTC training process. Note that OTC is an extension of BTC and supports all BTC functions. Therefore, in the following, we only describe OTC. @@ -130,6 +130,8 @@ export CUDA_VISIBLE_DEVICES="0" --lm-dir "${lm_dir}" \ --otc-token "${otc_token}" ``` +### Results (ctc-greedy-search) + ## Citations ``` From c83e278d8bc3e7004f0b900e242173611e0a8282 Mon Sep 17 00:00:00 2001 From: Dongji Gao Date: Tue, 19 Sep 2023 14:18:13 -0400 Subject: [PATCH 3/3] Update README.md with results --- egs/librispeech/WSASR/README.md | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/egs/librispeech/WSASR/README.md b/egs/librispeech/WSASR/README.md index adcf201c3..888105b3c 100644 --- a/egs/librispeech/WSASR/README.md +++ b/egs/librispeech/WSASR/README.md @@ -130,7 +130,18 @@ export CUDA_VISIBLE_DEVICES="0" --lm-dir "${lm_dir}" \ --otc-token "${otc_token}" ``` + ### Results (ctc-greedy-search) +| Traning Criterion | test-clean | test-other | +|------------|:-------:|:----:| +| CTC |100.0|100.0 | +| OTC | 11.89 | 25.46 | + +### Results (1best, blank_bias=-4) +| Traning Criterion | test-clean | test-other | +|------------|:-------:|:----:| +| CTC |98.40|98.68 | +| OTC | 6.59 | 15.98 | ## Citations