Merge r1.10.0 main (NVIDIA#4448)

* update branch Signed-off-by: ericharper <complex451@gmail.com> * Fix ASR Typos in tutorials (NVIDIA#4384) * Fix typos Signed-off-by: smajumdar <smajumdar@nvidia.com> * Quick wav2vec fix. In-place operation adding convolutional positions to encoder was overwriting leaf history. Wasn't caught on previous torch versions. (NVIDIA#4383) Signed-off-by: tbartley94 <tbartley@nvidia.com> Co-authored-by: tbartley94 <tbartley@nvidia.com> (cherry picked from commit 0322b15) Co-authored-by: Travis Bartley <Travismbartley@gmail.com> * Punctuation and capitalization tests race condition (NVIDIA#4399) * Add draft of race condition fixes Signed-off-by: PeganovAnton <peganoff2@mail.ru> * Minor improvements Signed-off-by: PeganovAnton <peganoff2@mail.ru> * More race condition fixes Signed-off-by: PeganovAnton <peganoff2@mail.ru> * Improve error message Signed-off-by: PeganovAnton <peganoff2@mail.ru> * Improve error message Signed-off-by: PeganovAnton <peganoff2@mail.ru> * Improve error message Signed-off-by: PeganovAnton <peganoff2@mail.ru> * Fix tutorial typos and docs (NVIDIA#4415) * Fix typos Signed-off-by: smajumdar <smajumdar@nvidia.com> * Fix typos Signed-off-by: smajumdar <smajumdar@nvidia.com> * Add reconfigure on validation epoch start (NVIDIA#4393) * Add reconfigure on validation epoch start Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Style Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * Remove pdb Signed-off-by: MaximumEntropy <sandeep.subramanian.1@umontreal.ca> * switch branch (NVIDIA#4424) Signed-off-by: fayejf <fayejf07@gmail.com> * Add ASR Scores to Docs (NVIDIA#4412) * Fix link Signed-off-by: smajumdar <smajumdar@nvidia.com> * Correct model card Signed-off-by: smajumdar <smajumdar@nvidia.com> * Add ASR Results to Docs Signed-off-by: smajumdar <smajumdar@nvidia.com> * Update info Signed-off-by: smajumdar <smajumdar@nvidia.com> * Update info Signed-off-by: smajumdar <smajumdar@nvidia.com> * Re-apply fixes from r1.9.0 (NVIDIA#4425) Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> * Replace all with /content/ (NVIDIA#4427) Signed-off-by: smajumdar <smajumdar@nvidia.com> * Fix hanging issue by multiprocessing in SD tutorial and add ETA for VAD processing (NVIDIA#4405) * cherry-pick pr 4317 and avoid signoff issue Signed-off-by: fayejf <fayejf07@gmail.com> * workaround for mp nb issue Signed-off-by: fayejf <fayejf07@gmail.com> * tdqm for mp functions in vad_utils Signed-off-by: fayejf <fayejf07@gmail.com> * style fix Signed-off-by: fayejf <fayejf07@gmail.com> * reflect comment Signed-off-by: fayejf <fayejf07@gmail.com> * remove Signed-off-by: fayejf <fayejf07@gmail.com> * [NLP] P&C Fix multi node cache issue, add pynini guard (NVIDIA#4410) * add sleep to fix multi node cache issue, add pynini guard Signed-off-by: ekmb <ebakhturina@nvidia.com> * fix lgtm Signed-off-by: ekmb <ebakhturina@nvidia.com> * add tempfile Signed-off-by: ekmb <ebakhturina@nvidia.com> * savfe tmp file to the same dir Signed-off-by: ekmb <ebakhturina@nvidia.com> Co-authored-by: PeganovAnton <peganoff2@mail.ru> * fix the notebook (NVIDIA#4438) Signed-off-by: Yi Dong <yidong@nvidia.com> * update nemo version dialogue tutorial (NVIDIA#4437) * docs: add table overflow handling for nested sections (NVIDIA#4441) Co-authored-by: Nick Goncharenko <ngoncharenko@nvidia.com> * Docs: Decrease Font Size on Tables (NVIDIA#4444) * docs: add table overflow handling for nested sections * docs: set table font-size to small Co-authored-by: Nick Goncharenko <ngoncharenko@nvidia.com> * unify intent slot dataset util functions in tutorials (NVIDIA#4445) * Notebook bug fix: add subfolder (NVIDIA#4442) * add subfolder Signed-off-by: ekmb <ebakhturina@nvidia.com> * exp_dir update Signed-off-by: ekmb <ebakhturina@nvidia.com> Co-authored-by: Eric Harper <complex451@gmail.com> * Fix typo in HiFi-GAN config's max steps (NVIDIA#4446) Signed-off-by: Jocelyn Huang <jocelynh@nvidia.com> Co-authored-by: Eric Harper <complex451@gmail.com> * Updated notebook to fix batch configuration and precision bugs (NVIDIA#4447) * Updated notebook to fix batch configuration and precision bugs Signed-off-by: Virginia Adams <vadams@nvidia.com> * Deleted cell outputs Signed-off-by: Virginia Adams <vadams@nvidia.com> * Set datasets back to full dataset Signed-off-by: Virginia Adams <vadams@nvidia.com> Co-authored-by: Eric Harper <complex451@gmail.com> * update branch Signed-off-by: ericharper <complex451@gmail.com> Co-authored-by: Somshubra Majumdar <titu1994@gmail.com> Co-authored-by: Travis Bartley <Travismbartley@gmail.com> Co-authored-by: PeganovAnton <peganoff2@mail.ru> Co-authored-by: Sandeep Subramanian <sandeep.subramanian.1@umontreal.ca> Co-authored-by: fayejf <36722593+fayejf@users.noreply.github.com> Co-authored-by: Jocelyn <jocelynh@nvidia.com> Co-authored-by: Evelina <10428420+ekmb@users.noreply.github.com> Co-authored-by: Yi Dong <43824965+yidong72@users.noreply.github.com> Co-authored-by: Zhilin Wang <wangzhilin12061996@hotmail.com> Co-authored-by: Nick Goncharenko <8766167+nickolyamba@users.noreply.github.com> Co-authored-by: Nick Goncharenko <ngoncharenko@nvidia.com> Co-authored-by: Virginia Adams <78445382+vadam5@users.noreply.github.com> Signed-off-by: David Mosallanezhad <dmosallanezh@nvidia.com>
Davood-M · Aug 9, 2022 · f117e7f · f117e7f
1 parent e59478a
commit f117e7f
Show file tree

Hide file tree

Showing 55 changed files with 667 additions and 610 deletions.
diff --git a/Jenkinsfile b/Jenkinsfile
@@ -734,7 +734,7 @@ pipeline {
             exp_manager=null'
           }
         }
-        stage('Test Restore with AlBERT') {
+        stage('Test Restore Punctuation & Capitalization with AlBERT') {
           steps {
             sh 'data_dir="$(mktemp -d -p "$(pwd)")" && \
             cp /home/TestData/nlp/token_classification_punctuation/*.txt "${data_dir}"/ && \
@@ -752,7 +752,7 @@ pipeline {
             rm -rf "${data_dir}"'
           }
         }
-        stage('Test Restore with RoBERTa') {
+        stage('Test Restore Punctuation & Capitalization with RoBERTa') {
           steps {
             sh 'data_dir="$(mktemp -d -p "$(pwd)")" && \
             cp /home/TestData/nlp/token_classification_punctuation/*.txt "${data_dir}"/ && \
@@ -763,7 +763,7 @@ pipeline {
               +model.test_ds.use_cache=false \
               ~model.train_ds \
               ~model.validation_ds \
-              model.test_ds.ds_item=/home/TestData/nlp/token_classification_punctuation/ \
+              model.test_ds.ds_item="${data_dir}" \
               trainer.devices=[1] \
               trainer.accelerator="gpu" \
               exp_manager=null && \
@@ -1593,17 +1593,23 @@ pipeline {
         stage('Punctuation & Capitalization, Using model.common_datasest_parameters.label_vocab_dir') {
           steps {
             sh 'cd examples/nlp/token_classification && \
-            label_vocab_dir=label_vocab_dir && \
+            work_dir="$(mktemp -d -p "$(pwd)")" && \
+            label_vocab_dir="${work_dir}/labels" && \
             mkdir -p ${label_vocab_dir} && \
+            data_dir="${work_dir}/data" && \
+            mkdir -p "${data_dir}" && \
+            cp /home/TestData/nlp/token_classification_punctuation/*.txt "${data_dir}" && \
+            output_dir="${work_dir}/output" && \
+            mkdir -p "${output_dir}" && \
             punct_label_vocab="${label_vocab_dir}/punct_label_vocab.csv" && \
             capit_label_vocab="${label_vocab_dir}/capit_label_vocab.csv" && \
             printf "O\n,\n.\n?\n" > "${punct_label_vocab}" && \
             printf "O\nU\n" > "${capit_label_vocab}" && \
-            CUDA_LAUNCH_BLOCKING=1 python punctuation_capitalization_train_evaluate.py \
+            python punctuation_capitalization_train_evaluate.py \
               model.train_ds.use_tarred_dataset=false \
-              model.train_ds.ds_item=/home/TestData/nlp/token_classification_punctuation \
-              model.validation_ds.ds_item=/home/TestData/nlp/token_classification_punctuation \
-              model.test_ds.ds_item=/home/TestData/nlp/token_classification_punctuation \
+              model.train_ds.ds_item="${data_dir}" \
+              model.validation_ds.ds_item="${data_dir}" \
+              model.test_ds.ds_item="${data_dir}" \
               model.language_model.pretrained_model_name=distilbert-base-uncased \
               model.common_dataset_parameters.label_vocab_dir="${label_vocab_dir}" \
               model.class_labels.punct_labels_file="$(basename "${punct_label_vocab}")" \
@@ -1614,68 +1620,71 @@ pipeline {
               trainer.devices=[0,1] \
               trainer.strategy=ddp \
               trainer.max_epochs=1 \
-              +exp_manager.explicit_log_dir=/home/TestData/nlp/token_classification_punctuation/output \
+              +exp_manager.explicit_log_dir="${output_dir}" \
               +do_testing=false && \
-            CUDA_LAUNCH_BLOCKING=1 python punctuation_capitalization_train_evaluate.py \
+            python punctuation_capitalization_train_evaluate.py \
               +do_training=false \
               +do_testing=true \
               ~model.train_ds \
               ~model.validation_ds \
-              model.test_ds.ds_item=/home/TestData/nlp/token_classification_punctuation \
-              pretrained_model=/home/TestData/nlp/token_classification_punctuation/output/checkpoints/Punctuation_and_Capitalization.nemo \
+              model.test_ds.ds_item="${data_dir}" \
+              pretrained_model="${output_dir}/checkpoints/Punctuation_and_Capitalization.nemo" \
               +model.train_ds.use_cache=false \
               +model.validation_ds.use_cache=false \
               +model.test_ds.use_cache=false \
               trainer.devices=[0,1] \
               trainer.strategy=ddp \
               trainer.max_epochs=1 \
               exp_manager=null && \
-            rm -r "${label_vocab_dir}" && \
-            rm -rf /home/TestData/nlp/token_classification_punctuation/output/*'
+            rm -rf "${work_dir}"'
           }
         }
         stage('Punctuation & Capitalization, Using model.common_datasest_parameters.{punct,capit}_label_ids') {
           steps {
             sh 'cd examples/nlp/token_classification && \
-            conf_path=/home/TestData/nlp/token_classification_punctuation && \
+            work_dir="$(mktemp -d -p "$(pwd)")" && \
+            output_dir="${work_dir}/output" && \
+            mkdir -p "${output_dir}" && \
+            data_dir="${work_dir}/data" && \
+            mkdir -p "${data_dir}" && \
+            cp /home/TestData/nlp/token_classification_punctuation/*.txt "${data_dir}" && \
             conf_name=punctuation_capitalization_config_with_ids && \
-            cp conf/punctuation_capitalization_config.yaml "${conf_path}/${conf_name}.yaml" && \
+            cp conf/punctuation_capitalization_config.yaml "${work_dir}/${conf_name}.yaml" && \
             sed -i $\'s/punct_label_ids: null/punct_label_ids: {O: 0, \\\',\\\': 1, .: 2, \\\'?\\\': 3}/\' \
-              "${conf_path}/${conf_name}.yaml" && \
+              "${work_dir}/${conf_name}.yaml" && \
             sed -i $\'s/capit_label_ids: null/capit_label_ids: {O: 0, U: 1}/\' \
-              "${conf_path}/${conf_name}.yaml" && \
-            CUDA_LAUNCH_BLOCKING=1 python punctuation_capitalization_train_evaluate.py \
-              --config-path "${conf_path}" \
+              "${work_dir}/${conf_name}.yaml" && \
+            python punctuation_capitalization_train_evaluate.py \
+              --config-path "${work_dir}" \
               --config-name "${conf_name}" \
               model.train_ds.use_tarred_dataset=false \
-              model.train_ds.ds_item=/home/TestData/nlp/token_classification_punctuation \
-              model.validation_ds.ds_item=/home/TestData/nlp/token_classification_punctuation \
-              model.test_ds.ds_item=/home/TestData/nlp/token_classification_punctuation \
+              model.train_ds.ds_item="${data_dir}" \
+              model.validation_ds.ds_item="${data_dir}" \
+              model.test_ds.ds_item="${data_dir}" \
               model.language_model.pretrained_model_name=distilbert-base-uncased \
               +model.train_ds.use_cache=false \
               +model.validation_ds.use_cache=false \
               +model.test_ds.use_cache=false \
               trainer.devices=[0,1] \
               trainer.strategy=ddp \
               trainer.max_epochs=1 \
-              +exp_manager.explicit_log_dir=/home/TestData/nlp/token_classification_punctuation/output \
+              +exp_manager.explicit_log_dir="${output_dir}" \
               +do_testing=false && \
-            CUDA_LAUNCH_BLOCKING=1 python punctuation_capitalization_train_evaluate.py \
+            python punctuation_capitalization_train_evaluate.py \
               +do_training=false \
               +do_testing=true \
               ~model.train_ds \
               ~model.validation_ds \
-              model.test_ds.ds_item=/home/TestData/nlp/token_classification_punctuation \
-              pretrained_model=/home/TestData/nlp/token_classification_punctuation/output/checkpoints/Punctuation_and_Capitalization.nemo \
+              model.test_ds.ds_item="${data_dir}" \
+              pretrained_model="${output_dir}/checkpoints/Punctuation_and_Capitalization.nemo" \
               +model.train_ds.use_cache=false \
               +model.validation_ds.use_cache=false \
               +model.test_ds.use_cache=false \
               trainer.devices=[0,1] \
               trainer.strategy=ddp \
               trainer.max_epochs=1 \
               exp_manager=null && \
-            rm -rf /home/TestData/nlp/token_classification_punctuation/output/* && \
-            rm "${conf_path}/${conf_name}.yaml"'
+            rm -rf "${work_dir}"'
           }
         }
       }

diff --git a/docs/source/_static/css/custom.css b/docs/source/_static/css/custom.css
@@ -58,8 +58,19 @@ a:visited
 	margin-left: unset;
 }
 
+section {
+	overflow-x: auto;
+}
 
 /* ----------------------------------------------TABLES--------------------------------------- */
+section table {
+	overflow-x: auto;
+	display: block;
+}
+
+table {
+	font-size: small;
+}
 
 /* Table head Color */
 thead td

diff --git a/docs/source/asr/data/scores/ca/quartznet15x5_ca.csv b/docs/source/asr/data/scores/ca/quartznet15x5_ca.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (ca)
+stt_ca_quartznet15x5,ca,6.0
diff --git a/docs/source/asr/data/scores/de/citrinet_de.csv b/docs/source/asr/data/scores/de/citrinet_de.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (de),MCV Dev-Set v7.0 (de),MCV Test-Set v7.0 (de),MLS Dev (en),MLS Test (en),VoxPopuli Dev (de),VoxPopuli Test (de)
+stt_de_citrinet_1024,de,,6.63,7.59,4.06,5.07,12.33,10.02
diff --git a/docs/source/asr/data/scores/de/conformer_de.csv b/docs/source/asr/data/scores/de/conformer_de.csv
@@ -0,0 +1,3 @@
+Model Name,Language,MCV Dev-Set (v??) (de),MCV Dev-Set v7.0 (de),MCV Test-Set v7.0 (de),MLS Dev (en),MLS Test (en),VoxPopuli Dev (de),VoxPopuli Test (de)
+stt_de_conformer_ctc_large,de,,5.84,6.68,3.85,4.63,12.56,10.51
+stt_de_conformer_transducer_large,de,,4.75,5.36,3.46,4.19,11.21,9.14
diff --git a/docs/source/asr/data/scores/de/contextnet_de.csv b/docs/source/asr/data/scores/de/contextnet_de.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (de),MCV Dev-Set v7.0 (de),MCV Test-Set v7.0 (de),MLS Dev (en),MLS Test (en),VoxPopuli Dev (de),VoxPopuli Test (de)
+stt_de_contextnet_1024,de,,4.76,5.5,3.53,4.2,11.32,9.4
diff --git a/docs/source/asr/data/scores/de/quartznet15x5_de.csv b/docs/source/asr/data/scores/de/quartznet15x5_de.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (de),MCV Dev-Set v7.0 (de),MCV Test-Set v7.0 (de),MLS Dev (en),MLS Test (en),VoxPopuli Dev (de),VoxPopuli Test (de)
+stt_de_quartznet15x5,de,11.78,,,,,,
diff --git a/docs/source/asr/data/scores/en/citrinet_en.csv b/docs/source/asr/data/scores/en/citrinet_en.csv
@@ -0,0 +1,7 @@
+Model Name,Language,Librispeech Dev-Clean,Librispeech Dev-Other,Librispeech Test-Clean,Librispeech Test-Other,MCV Test-Set v8.0 (en),MLS Dev (en),MLS Test (en),NSC Part1,NSC Part6,Peoples Speech Test v1,SLR 83 Test,WSJ Dev 93,WSJ Eval 92
+stt_en_citrinet_256,en,4.2 % WER,10.7 % WER,4.4 % WER,10.7 % WER,,,,,,,,,
+stt_en_citrinet_512,en,3.7 % WER,8.9 % WER,3.7 % WER,8.9 % WER,,,,,,,,,
+stt_en_citrinet_1024,en,3.7 % WER,8.3 % WER,3.6 % WER,7.9 % WER,,,,,,,,,
+stt_en_citrinet_256_gamma_0_25,en,4.7 %,10.6 %,4.8 %,10.7 %,,,,8.3 %,,,,5.8 %,3.6 %
+stt_en_citrinet_512_gamma_0_25,en,4.0 %,9.0 %,3.9 %,9.0 %,,,,6.9 %,,,,4.4 %,3.6 %
+stt_en_citrinet_1024_gamma_0_25,en,3.4 %,7.7 %,3.4 %,7.6 %,,,,6.2 %,,,,4.0 %,2.5 %
diff --git a/docs/source/asr/data/scores/en/conformer_en.csv b/docs/source/asr/data/scores/en/conformer_en.csv
@@ -0,0 +1,14 @@
+Model Name,Language,Librispeech Dev-Clean,Librispeech Dev-Other,Librispeech Test-Clean,Librispeech Test-Other,MCV Test-Set v8.0 (en),MLS Dev (en),MLS Test (en),NSC Part1,NSC Part6,Peoples Speech Test v1,SLR 83 Test,WSJ Dev 93,WSJ Eval 92
+stt_en_conformer_ctc_small,en,3.6,8.1,3.7,8.1,,,,,,,,,
+stt_en_conformer_ctc_medium,en,2.5,5.8,2.6,5.9,,,,,,,,,
+stt_en_conformer_ctc_large,en,2.0,4.4,2.1,4.3,,,,,,,,,
+stt_en_conformer_ctc_xlarge,en,1.77 %,3.79 %,2.00 %,3.74 %,7.88 %,,5.99 %,,6.44 %,22.90 %,5.50 %,2.36 %,
+stt_en_conformer_ctc_small_ls,en,3.3,8.8,3.4,8.8,,,,,,,,,
+stt_en_conformer_ctc_medium_ls,en,2.7,7.4,3.0,7.3,,,,,,,,,
+stt_en_conformer_ctc_large_ls,en,2.4,6.2,2.7,6.0,,,,,,,,,
+stt_en_conformer_transducer_small,en,2.8,6.6,2.5,6.6,,,,,,,,,
+stt_en_conformer_transducer_medium,en,2.0,4.6,2.1,4.7,,,,,,,,,
+stt_en_conformer_transducer_large,en,1.5,3.5,1.7,3.6,,,,,,,,,
+stt_en_conformer_transducer_large_ls,en,2.1,5.0,2.3,5.1,,,,,,,,,
+stt_en_conformer_transducer_xlarge,en,1.48 %,2.95 %,1.62 %,3.01 %,6.46 %,4.59 %,5.32 %,5.70 %,6.47 %,21.32 %,,2.05 %,1.17 %
+stt_en_conformer_transducer_xxlarge,en,1.52 %,3.09 %,1.72 %,3.14 %,,5.29 %,5.85 %,6.64 %,,,,2.42 %,1.49 %
diff --git a/docs/source/asr/data/scores/en/contextnet_en.csv b/docs/source/asr/data/scores/en/contextnet_en.csv
@@ -0,0 +1,7 @@
+Model Name,Language,Librispeech Dev-Clean,Librispeech Dev-Other,Librispeech Test-Clean,Librispeech Test-Other,MCV Test-Set v8.0 (en),MLS Dev (en),MLS Test (en),NSC Part1,NSC Part6,Peoples Speech Test v1,SLR 83 Test,WSJ Dev 93,WSJ Eval 92
+stt_en_contextnet_256,en,3.3 %,7.9 %,3.3 %,8.0 %,,9.7 %,11.0 %,7.1 %,,,,4.6 %,3.2 %
+stt_en_contextnet_512,en,2.0 %,4.8 %,2.2 %,5.0 %,,6.6 %,7.3 %,5.9 %,,,,2.8 %,1.4 %
+stt_en_contextnet_1024,en,1.7 %,3.8 %,1.9 %,4.0 %,7.9 %,,5.9 %,5.2 %,6.5 %,21.7 %,4.7 %,2.3 %,1.3 %
+stt_en_contextnet_256_mls,en,,9.0 %,,9.2 %,,9.4 %,10.9 %,,,,,,
+stt_en_contextnet_512_mls,en,,5.2 %,,5.2 %,,5.6 %,6.6 %,,,,,,
+stt_en_contextnet_1024_mls,en,,4.1 %,,4.2 %,,4.6 %,5.6 %,,,,,,
diff --git a/docs/source/asr/data/scores/en/jasper10x5dr_en.csv b/docs/source/asr/data/scores/en/jasper10x5dr_en.csv
@@ -0,0 +1,2 @@
+Model Name,Language,Librispeech Dev-Clean,Librispeech Dev-Other,Librispeech Test-Clean,Librispeech Test-Other,MCV Test-Set v8.0 (en),MLS Dev (en),MLS Test (en),NSC Part1,NSC Part6,Peoples Speech Test v1,SLR 83 Test,WSJ Dev 93,WSJ Eval 92
+stt_en_jasper10x5dr,en,3.74,10.21,,,,,,,,,,,
diff --git a/docs/source/asr/data/scores/en/quartznet15x5_en.csv b/docs/source/asr/data/scores/en/quartznet15x5_en.csv
@@ -0,0 +1,2 @@
+Model Name,Language,Librispeech Dev-Clean,Librispeech Dev-Other,Librispeech Test-Clean,Librispeech Test-Other,MCV Test-Set v8.0 (en),MLS Dev (en),MLS Test (en),NSC Part1,NSC Part6,Peoples Speech Test v1,SLR 83 Test,WSJ Dev 93,WSJ Eval 92
+stt_en_quartznet15x5,en,4.38,11.3,,,,,,,,,,,
diff --git a/docs/source/asr/data/scores/enes/conformer_enes.csv b/docs/source/asr/data/scores/enes/conformer_enes.csv
@@ -0,0 +1,3 @@
+Model Name,Language,Fisher-Dev-Es,Librispeech Dev-Clean,Librispeech Dev-Other,Librispeech Test-Clean,Librispeech Test-Other,MCV Dev-Set v7.0 (en),MLS Dev (es),VoxPopuli Dev (es)
+stt_enes_conformer_ctc_large,enes,16.7 %,2.2 %,5.5 %,2.6 %,5.5 %,5.8 %,3.5 %,5.7 %
+stt_enes_conformer_transducer_large,enes,16.2 %,2.0 %,4.6 %,2.2 %,4.6 %,5.0 %,3.3 %,5.3 %
diff --git a/docs/source/asr/data/scores/enes/contextnet_enes.csv b/docs/source/asr/data/scores/enes/contextnet_enes.csv
@@ -0,0 +1,2 @@
+Model Name,Language,Fisher-Dev-Es,Librispeech Dev-Clean,Librispeech Dev-Other,Librispeech Test-Clean,Librispeech Test-Other,MCV Dev-Set v7.0 (en),MLS Dev (es),VoxPopuli Dev (es)
+stt_enes_contextnet_large,enes,14.8 %,2.2 %,5.6 %,2.3 %,5.5 %,4.7 %,3.0 %,5.0 %
diff --git a/docs/source/asr/data/scores/es/citrinet_es.csv b/docs/source/asr/data/scores/es/citrinet_es.csv
@@ -0,0 +1,3 @@
+Model Name,Language,Call Home Dev Test (es),Call Home Eval Test (es),Call Home Train (es),Fisher Dev Set (es),Fisher Test Set (es),MCV Dev-Set (v??) (es),MCV Dev-Set v7.0 (es),MCV Test-Set (v??) (es),MCV Test-Set v7.0 (es),MLS Dev (en),MLS Test (en),VoxPopuli Dev (es),VoxPopuli Test (es)
+stt_es_citrinet_512,es,,,,,,9.1 % WER,,10.3 % WER,,4.9 % WER,5.2 % WER,,
+stt_es_citrinet_1024_gamma_0_25,es,19.9 %,21.3 %,19.1 %,15.8 %,15.9 %,,6.1 %,,6.8 %,3.5 %,4.1 %,5.6 %,7.0 %
diff --git a/docs/source/asr/data/scores/es/conformer_es.csv b/docs/source/asr/data/scores/es/conformer_es.csv
@@ -0,0 +1,3 @@
+Model Name,Language,Call Home Dev Test (es),Call Home Eval Test (es),Call Home Train (es),Fisher Dev Set (es),Fisher Test Set (es),MCV Dev-Set (v??) (es),MCV Dev-Set v7.0 (es),MCV Test-Set (v??) (es),MCV Test-Set v7.0 (es),MLS Dev (en),MLS Test (en),VoxPopuli Dev (es),VoxPopuli Test (es)
+stt_es_conformer_ctc_large,es,23.7 %,25.3 %,22.4 %,18.3 %,18.5 %,,6.3 %,,6.9 %,4.3 %,4.2 %,6.1 %,7.5 %
+stt_es_conformer_transducer_large,es,18.0 %,19.4 %,17.2 %,14.7 %,14.8 %,,4.6 %,,5.2 %,2.7 %,3.2 %,4.7 %,6.0 %
diff --git a/docs/source/asr/data/scores/es/contextnet_es.csv b/docs/source/asr/data/scores/es/contextnet_es.csv
@@ -0,0 +1,2 @@
+Model Name,Language,Call Home Dev Test (es),Call Home Eval Test (es),Call Home Train (es),Fisher Dev Set (es),Fisher Test Set (es),MCV Dev-Set (v??) (es),MCV Dev-Set v7.0 (es),MCV Test-Set (v??) (es),MCV Test-Set v7.0 (es),MLS Dev (en),MLS Test (en),VoxPopuli Dev (es),VoxPopuli Test (es)
+stt_es_contextnet_1024,es,19.1 %,20.7 %,18.2 %,15.3 %,15.1 %,,4.8 %,,5.2 %,3.1 %,3.5 %,5.1 %,6.2 %
diff --git a/docs/source/asr/data/scores/es/quartznet15x5_es.csv b/docs/source/asr/data/scores/es/quartznet15x5_es.csv
@@ -0,0 +1,2 @@
+Model Name,Language,Call Home Dev Test (es),Call Home Eval Test (es),Call Home Train (es),Fisher Dev Set (es),Fisher Test Set (es),MCV Dev-Set (v??) (es),MCV Dev-Set v7.0 (es),MCV Test-Set (v??) (es),MCV Test-Set v7.0 (es),MLS Dev (en),MLS Test (en),VoxPopuli Dev (es),VoxPopuli Test (es)
+stt_es_quartznet15x5,es,,,,,,12.97,,,,,,,
diff --git a/docs/source/asr/data/scores/fr/citrinet_fr.csv b/docs/source/asr/data/scores/fr/citrinet_fr.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (fr),MCV Dev-Set v7.0 (fr),MCV Dev-Set v7.0 (fr) (No Hyphen),MCV Test-Set v7.0 (fr),MCV Test-Set v7.0 (fr) (No Hyphen),MLS Dev (en),MLS Dev (en) (No Hyphen),MLS Test (en),MLS Test (en) (No Hyphen)
+stt_fr_citrinet_1024_gamma_0_25,fr,,10.76,9.90,12.20,11.11,6.66,6.19,5.53,5.12
diff --git a/docs/source/asr/data/scores/fr/conformer_fr.csv b/docs/source/asr/data/scores/fr/conformer_fr.csv
@@ -0,0 +1,3 @@
+Model Name,Language,MCV Dev-Set (v??) (fr),MCV Dev-Set v7.0 (fr),MCV Dev-Set v7.0 (fr) (No Hyphen),MCV Test-Set v7.0 (fr),MCV Test-Set v7.0 (fr) (No Hyphen),MLS Dev (en),MLS Dev (en) (No Hyphen),MLS Test (en),MLS Test (en) (No Hyphen)
+stt_fr_conformer_ctc_large,fr,,8.35,7.88,9.63,9.01,5.88,5.90,4.91,4.63
+stt_fr_conformer_transducer_large,fr,,6.85,,7.95,,5.05,,4.10,
diff --git a/docs/source/asr/data/scores/fr/contextnet_fr.csv b/docs/source/asr/data/scores/fr/contextnet_fr.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (fr),MCV Dev-Set v7.0 (fr),MCV Dev-Set v7.0 (fr) (No Hyphen),MCV Test-Set v7.0 (fr),MCV Test-Set v7.0 (fr) (No Hyphen),MLS Dev (en),MLS Dev (en) (No Hyphen),MLS Test (en),MLS Test (en) (No Hyphen)
+stt_fr_contextnet_1024,fr,,8.32,,9.42,,6.02,,5.01,
diff --git a/docs/source/asr/data/scores/fr/quartznet15x5_fr.csv b/docs/source/asr/data/scores/fr/quartznet15x5_fr.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (fr),MCV Dev-Set v7.0 (fr),MCV Dev-Set v7.0 (fr) (No Hyphen),MCV Test-Set v7.0 (fr),MCV Test-Set v7.0 (fr) (No Hyphen),MLS Dev (en),MLS Dev (en) (No Hyphen),MLS Test (en),MLS Test (en) (No Hyphen)
+stt_fr_quartznet15x5,fr,14.01,,,,,,,,
diff --git a/docs/source/asr/data/scores/it/quartznet15x5_it.csv b/docs/source/asr/data/scores/it/quartznet15x5_it.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (it)
+stt_it_quartznet15x5,it,15.22
diff --git a/docs/source/asr/data/scores/pl/quartznet15x5_pl.csv b/docs/source/asr/data/scores/pl/quartznet15x5_pl.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (pl)
+stt_pl_quartznet15x5,pl,14
diff --git a/docs/source/asr/data/scores/ru/quartznet15x5_ru.csv b/docs/source/asr/data/scores/ru/quartznet15x5_ru.csv
@@ -0,0 +1,2 @@
+Model Name,Language,MCV Dev-Set (v??) (ru)
+stt_ru_quartznet15x5,ru,16.23
diff --git a/docs/source/asr/data/scores/zh/citrinet_zh.csv b/docs/source/asr/data/scores/zh/citrinet_zh.csv
@@ -0,0 +1,3 @@
+Model Name,Language,AIShell Dev-Android v2,AIShell Dev-Ios v1,AIShell Dev-Ios v2,AIShell Dev-Mic v2,AIShell Test-Android v2,AIShell Test-Ios v1,AIShell Test-Ios v2,AIShell Test-Mic v2
+stt_zh_citrinet_512,zh,,6.25%,,,,6.44%,,
+stt_zh_citrinet_1024_gamma_0_25,zh,5.2 %,,4.8 %,5.2 %,5.5 %,,5.1 %,5.5 %
diff --git a/docs/source/asr/data/scores/zh/conformer_zh.csv b/docs/source/asr/data/scores/zh/conformer_zh.csv
@@ -0,0 +1,2 @@
+Model Name,Language,AIShell Dev-Android v2,AIShell Dev-Ios v1,AIShell Dev-Ios v2,AIShell Dev-Mic v2,AIShell Test-Android v2,AIShell Test-Ios v1,AIShell Test-Ios v2,AIShell Test-Mic v2
+stt_zh_conformer_transducer_large,zh,3.4,,3.2,3.4,3.4,,3.2,3.4
diff --git a/docs/source/asr/intro.rst b/docs/source/asr/intro.rst
@@ -37,6 +37,7 @@ The full documentation tree is as follows:
    datasets
    asr_language_modeling
    results
+   scores
    configs
    api
    resources