NVIDIA-NeMo · nithinraok · Mar 23, 2026 · Mar 17, 2026 · Mar 17, 2026 · Mar 17, 2026
diff --git a/.github/workflows/cicd-main-speech.yml b/.github/workflows/cicd-main-speech.yml
@@ -86,10 +86,6 @@ jobs:
         include:
           - runner: self-hosted-azure-gpus-1
             script: ASR_dev_run_Speech_to_Text
-          - runner: self-hosted-azure-gpus-1
-            script: ASR_dev_run_Speech_to_Text_WPE_CitriNet
-          - runner: self-hosted-azure-gpus-1
-            script: ASR_dev_run_Speech_Pre-training_-_CitriNet
           - runner: self-hosted-azure-gpus-1
             script: Optional_ASR_dev_run_Speech_To_Text_Finetuning
             is-optional: true
@@ -100,8 +96,6 @@ jobs:
             script: ASR_dev_run_Speech_to_Text_WPE_-_Conformer
           - runner: self-hosted-azure-gpus-1
             script: ASR_dev_run_Speech_to_Text_Hybrid_RNNT_CTC_Prompt
-          - runner: self-hosted-azure-gpus-1
-            script: ASR_dev_run-part_two_Speech_to_Text_WPE_-_Squeezeformer
           - runner: self-hosted-azure-gpus-1
             script: L2_ASR_Multi-dataloader_dev_run_Speech_to_Text_multi-dataloader
           - runner: self-hosted-azure-gpus-1
@@ -154,8 +148,6 @@ jobs:
             timeout: 20
           - runner: self-hosted-azure-gpus-1
             script: L2_Speaker_dev_run_Speaker_Recognition
-          - runner: self-hosted-azure-gpus-1
-            script: L2_Speaker_dev_run_Speaker_Diarization
           - runner: self-hosted-azure-gpus-1
             script: L2_Speaker_dev_run_EndtoEnd_Speaker_Diarization_Sortformer
           - runner: self-hosted-azure
@@ -164,8 +156,6 @@ jobs:
             script: L2_Speaker_dev_run_Speaker_Diarization_with_ASR_Inference
           - runner: self-hosted-azure
             script: L2_Speaker_dev_run_Clustering_Diarizer_Inference
-          - runner: self-hosted-azure
-            script: L2_Speaker_dev_run_Neural_Diarizer_Inference
           - runner: self-hosted-azure
             script: L2_Speaker_dev_run_Multispeaker_ASR_Data_Simulation
           - runner: self-hosted-azure

diff --git a/docs/source/asr/api.rst b/docs/source/asr/api.rst
@@ -67,11 +67,6 @@ Modules
     :show-inheritance:
     :members:
 
-.. _squeezeformer-encoder-api:
-
-.. autoclass:: nemo.collections.asr.modules.SqueezeformerEncoder
-    :show-inheritance:
-    :members:
 
 .. _rnn-encoder-api:
 
@@ -100,15 +95,6 @@ Modules
     :members:
 
 
-
-Parts
------
-
-.. autoclass:: nemo.collections.asr.parts.submodules.jasper.JasperBlock
-    :show-inheritance:
-    :members:
-
-
 Mixins
 ------
 

diff --git a/docs/source/asr/configs.rst b/docs/source/asr/configs.rst
diff --git a/docs/source/asr/data/benchmark_by.csv b/docs/source/asr/data/benchmark_by.csv
@@ -1,4 +1,3 @@
 Model,Model Base Class
-`stt_uk_citrinet_1024_gamma_0_25 <https://huggingface.co/nvidia/stt_uk_citrinet_1024_gamma_0_25>`_,EncDecCTCModel
 `stt_ua_fastconformer_hybrid_large_pc <https://huggingface.co/nvidia/stt_ua_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
diff --git a/docs/source/asr/data/benchmark_cn.csv b/docs/source/asr/data/benchmark_cn.csv
@@ -1,3 +1,2 @@
 Model,Model Base Class
-`stt_zh_citrinet_1024_gamma_0_25 <https://huggingface.co/nvidia/stt_zh_citrinet_1024_gamma_0_25>`_,EncDecCTCModel
 `stt_zh_conformer_transducer_large <https://huggingface.co/nvidia/stt_zh_conformer_transducer_large>`_,EncDecRNNTBPEModel
diff --git a/docs/source/asr/data/benchmark_cs.csv b/docs/source/asr/data/benchmark_cs.csv
@@ -2,4 +2,3 @@ Model,Model Base Class
 `canary-1b-v2 <https://huggingface.co/nvidia/canary-1b-v2>`_,EncDecMultiTaskModel
 `stt_ca_conformer_ctc_large <https://huggingface.co/nvidia/stt_ca_conformer_ctc_large>`_,EncDecCTCModelBPE
 `stt_ca_conformer_transducer_large <https://huggingface.co/nvidia/stt_ca_conformer_transducer_large>`_,EncDecRNNTBPEModel
-`stt_ca_quartznet15x5 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_ca_quartznet15x5>`_,EncDecCTCModel
diff --git a/docs/source/asr/data/benchmark_de.csv b/docs/source/asr/data/benchmark_de.csv
@@ -4,8 +4,6 @@ Model,Model Base Class
 `stt_de_fastconformer_hybrid_large_pc <https://huggingface.co/nvidia/stt_de_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
 `stt_de_conformer_ctc_large <https://huggingface.co/nvidia/stt_de_conformer_ctc_large>`_,EncDecCTCModelBPE
 `stt_de_conformer_transducer_large <https://huggingface.co/nvidia/stt_de_conformer_transducer_large>`_,EncDecRNNTBPEModel
-`stt_de_quartznet15x5 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_de_quartznet15x5>`_,EncDecCTCModel
-`stt_de_contextnet_1024 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_de_contextnet_1024>`_,EncDecRNNTBPEModel
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
 `stt_multilingual_fastconformer_hybrid_large_pc_blend_eu <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc_blend_eu>`_,EncDecHybridRNNTCTCBPEModel
 `canary-1b-flash <https://huggingface.co/nvidia/canary-1b-flash>`_,EncDecMultiTaskModel

diff --git a/docs/source/asr/data/benchmark_en.csv b/docs/source/asr/data/benchmark_en.csv
@@ -9,34 +9,19 @@ Model,Model Base Class
 `parakeet-ctc-1.1b <https://huggingface.co/nvidia/parakeet-ctc-1.1b>`_, EncDecCTCModelBPE
 `stt_en_conformer_transducer_xlarge <https://huggingface.co/nvidia/stt_en_conformer_transducer_xlarge>`_, EncDecRNNTBPEModel
 `stt_en_fastconformer_ctc_large <https://huggingface.co/nvidia/stt_en_fastconformer_ctc_large>`_, EncDecCTCModelBPE
-`stt_en_citrinet_256_ls <https://huggingface.co/nvidia/stt_en_citrinet_256_ls>`_, EncDecCTCModelBPE
 `stt_en_fastconformer_hybrid_large_streaming_multi <https://huggingface.co/nvidia/stt_en_fastconformer_hybrid_large_streaming_multi>`_, EncDecHybridRNNTCTCBPEModel
 `stt_en_fastconformer_ctc_xxlarge <https://huggingface.co/nvidia/stt_en_fastconformer_ctc_xxlarge>`_, EncDecCTCTBPEModel
 `stt_en_conformer_transducer_large <https://huggingface.co/nvidia/stt_en_conformer_transducer_large>`_, EncDecRNNTBPEModel
 `stt_en_fastconformer_hybrid_large_pc <https://huggingface.co/nvidia/stt_en_fastconformer_hybrid_large_pc>`_, EncDecHybridRNNTCTCBPEModel
-`stt_en_citrinet_512_ls <https://huggingface.co/nvidia/stt_en_citrinet_512_ls>`_, EncDecCTCModelBPE
 `stt_en_conformer_ctc_small <https://huggingface.co/nvidia/stt_en_conformer_ctc_small>`_, EncDecCTCModelBPE
-`stt_en_citrinet_1024_gamma_0_25 <https://huggingface.co/nvidia/stt_en_citrinet_1024_gamma_0_25>`_, EncDecCTCModelBPE
 `stt_en_fastconformer_transducer_large <https://huggingface.co/nvidia/stt_en_fastconformer_transducer_large>`_, EncDecRNNTBPEModel
 `stt_en_fastconformer_transducer_xlarge <https://huggingface.co/nvidia/stt_en_fastconformer_transducer_xlarge>`_, EncDecRNNTBPEModel
 `stt_en_fastconformer_transducer_xxlarge <https://huggingface.co/nvidia/stt_en_fastconformer_transducer_xxlarge>`_, EncDecRNNTBPEModel
-`stt_en_citrinet_768_ls <https://huggingface.co/nvidia/stt_en_citrinet_768_ls>`_, EncDecCTCModelBPE
 `stt_en_fastconformer_ctc_xlarge <https://huggingface.co/nvidia/stt_en_fastconformer_ctc_xlarge>`_, EncDecCTCTBPEModel
-`stt_en_citrinet_384_ls <https://huggingface.co/nvidia/stt_en_citrinet_384_ls>`_, EncDecCTCModelBPE
-`stt_en_citrinet_1024_ls <https://huggingface.co/nvidia/stt_en_citrinet_1024_ls>`_, EncDecCTCModelBPE
-`QuartzNet15x5Base-En <https://ngc.nvidia.com/catalog/models/nvidia:nemospeechmodels>`_, EncDecCTCModel
-`stt_en_jasper10x5dr <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_en_jasper10x5dr>`_, EncDecCTCModel
-`stt_en_contextnet_256_mls <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_en_contextnet_256_mls>`_, EncDecRNNTBPEModel
-`stt_en_contextnet_512_mls <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_en_contextnet_512_mls>`_, EncDecRNNTBPEModel
-`stt_en_contextnet_1024_mls <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_en_contextnet_1024_mls>`_, EncDecRNNTBPEModel
-`stt_en_contextnet_256 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_en_contextnet_256>`_, EncDecRNNTBPEModel
-`stt_en_contextnet_512 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_en_contextnet_512>`_, EncDecRNNTBPEModel
-`stt_en_contextnet_1024 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_en_contextnet_1024>`_, EncDecRNNTBPEModel
 `stt_enes_conformer_ctc_large <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_enes_conformer_ctc_large>`_, EncDecCTCModelBPE
 `stt_enes_conformer_transducer_large <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_enes_conformer_transducer_large>`_, EncDecRNNTBPEModel
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_, EncDecHybridRNNTCTCBPEModel
 `stt_multilingual_fastconformer_hybrid_large_pc_blend_eu <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc_blend_eu>`_, EncDecHybridRNNTCTCBPEModel
-`slu_conformer_transformer_large_slurp <https://huggingface.co/nvidia/slu_conformer_transformer_large_slurp>`_, SLUIntentSlotBPEModel
 `canary-1b-flash <https://huggingface.co/nvidia/canary-1b-flash>`_, EncDecMultiTaskModel
 `low-frame-rate-speech-codec-22khz <https://huggingface.co/nvidia/low-frame-rate-speech-codec-22khz>`_, EncDecCTCModelBPE
 `stt_en_fastconformer_hybrid_medium_streaming_80ms_pc <https://huggingface.co/nvidia/stt_en_fastconformer_hybrid_medium_streaming_80ms_pc>`_, EncDecHybridRNNTCTCBPEModel

diff --git a/docs/source/asr/data/benchmark_es.csv b/docs/source/asr/data/benchmark_es.csv
@@ -4,8 +4,6 @@ Model,Model Base Class
 `stt_es_fastconformer_hybrid_large_pc <https://huggingface.co/nvidia/stt_es_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
 `stt_es_conformer_transducer_large <https://huggingface.co/nvidia/stt_es_conformer_transducer_large>`_,EncDecRNNTBPEModel
 `stt_es_conformer_ctc_large <https://huggingface.co/nvidia/stt_es_conformer_ctc_large>`_,EncDecCTCModelBPE
-`stt_es_quartznet15x5 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_es_quartznet15x5>`_,EncDecCTCModel
-`stt_es_contextnet_1024 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_es_contextnet_1024>`_,EncDecRNNTBPEModel
 `stt_enes_conformer_ctc_large <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_enes_conformer_ctc_large>`_,EncDecCTCModelBPE
 `stt_enes_conformer_transducer_large <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_enes_conformer_transducer_large>`_,EncDecRNNTBPEModel
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel

diff --git a/docs/source/asr/data/benchmark_fr.csv b/docs/source/asr/data/benchmark_fr.csv
@@ -4,9 +4,6 @@ Model,Model Base Class
 `stt_fr_conformer_ctc_large <https://huggingface.co/nvidia/stt_fr_conformer_ctc_large>`_,EncDecCTCModelBPE
 `stt_fr_fastconformer_hybrid_large_pc <https://huggingface.co/nvidia/stt_fr_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
 `stt_fr_conformer_transducer_large <https://huggingface.co/nvidia/stt_fr_conformer_transducer_large>`_,EncDecRNNTBPEModel
-`stt_fr_quartznet15x5 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_fr_quartznet15x5>`_,EncDecCTCModel
-`stt_fr_contextnet_1024 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_fr_contextnet_1024>`_,EncDecRNNTBPEModel
-`stt_fr_no_hyphen_citrinet_1024_gamma_0_25 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_fr_citrinet_1024_gamma_0_25>`_,EncDecCTCModelBPE
 `stt_fr_no_hyphen_conformer_ctc_large <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_fr_conformer_ctc_large>`_,EncDecCTCModelBPE
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
 `stt_multilingual_fastconformer_hybrid_large_pc_blend_eu <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc_blend_eu>`_,EncDecHybridRNNTCTCBPEModel

diff --git a/docs/source/asr/data/benchmark_it.csv b/docs/source/asr/data/benchmark_it.csv
@@ -3,5 +3,4 @@ Model,Model Base Class
 `stt_it_fastconformer_hybrid_large_pc <https://huggingface.co/nvidia/stt_it_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
 `stt_it_conformer_ctc_large <https://huggingface.co/nvidia/stt_it_conformer_ctc_large>`_,EncDecCTCModelBPE
 `stt_it_conformer_transducer_large <https://huggingface.co/nvidia/stt_it_conformer_transducer_large>`_,EncDecRNNTBPEModel
-`stt_it_quartznet15x5 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_it_quartznet15x5>`_,EncDecCTCModel
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
diff --git a/docs/source/asr/data/benchmark_pl.csv b/docs/source/asr/data/benchmark_pl.csv
@@ -1,5 +1,4 @@
 Model,Model Base Class
 `canary-1b-v2 <https://huggingface.co/nvidia/canary-1b-v2>`_,EncDecMultiTaskModel
 `stt_pl_fastconformer_hybrid_large_pc <https://huggingface.co/nvidia/stt_pl_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
-`stt_pl_quartznet15x5 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_pl_quartznet15x5>`_,EncDecCTCModel
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
diff --git a/docs/source/asr/data/benchmark_ru.csv b/docs/source/asr/data/benchmark_ru.csv
@@ -4,5 +4,4 @@ Model,Model Base Class
 `stt_ru_conformer_transducer_large <https://huggingface.co/nvidia/stt_ru_conformer_transducer_large>`_,EncDecRNNTBPEModel
 `stt_kk_ru_fastconformer_hybrid_large <https://huggingface.co/nvidia/stt_kk_ru_fastconformer_hybrid_large>`_,EncDecHybridRNNTCTCBPEModel
 `stt_ru_conformer_ctc_large <https://huggingface.co/nvidia/stt_ru_conformer_ctc_large>`_,EncDecCTCModelBPE
-`stt_ru_quartznet15x5 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_ru_quartznet15x5>`_,EncDecCTCModel
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
diff --git a/docs/source/asr/data/benchmark_ua.csv b/docs/source/asr/data/benchmark_ua.csv
@@ -1,5 +1,4 @@
 Model,Model Base Class
 `canary-1b-v2 <https://huggingface.co/nvidia/canary-1b-v2>`_,EncDecMultiTaskModel
-`stt_uk_citrinet_1024_gamma_0_25 <https://huggingface.co/nvidia/stt_uk_citrinet_1024_gamma_0_25>`_,EncDecCTCModel
 `stt_ua_fastconformer_hybrid_large_pc <https://huggingface.co/nvidia/stt_ua_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
 `stt_multilingual_fastconformer_hybrid_large_pc <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_multilingual_fastconformer_hybrid_large_pc>`_,EncDecHybridRNNTCTCBPEModel
diff --git a/docs/source/asr/data/benchmark_zh.csv b/docs/source/asr/data/benchmark_zh.csv
@@ -1,4 +1,2 @@
 Model,Model Base Class
-`stt_zh_citrinet_512 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_zh_citrinet_512>`_,EncDecCTCModel
-`stt_zh_citrinet_1024_gamma_0_25 <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_zh_citrinet_1024_gamma_0_25>`_,EncDecCTCModel
 `stt_zh_conformer_transducer_large <https://ngc.nvidia.com/catalog/models/nvidia:nemo:stt_zh_conformer_transducer_large>`_,EncDecRNNTModel
diff --git a/docs/source/asr/data/scores/ca/quartznet15x5_ca.csv b/docs/source/asr/data/scores/ca/quartznet15x5_ca.csv
diff --git a/docs/source/asr/data/scores/de/citrinet_de.csv b/docs/source/asr/data/scores/de/citrinet_de.csv
diff --git a/docs/source/asr/data/scores/de/contextnet_de.csv b/docs/source/asr/data/scores/de/contextnet_de.csv
diff --git a/docs/source/asr/data/scores/de/quartznet15x5_de.csv b/docs/source/asr/data/scores/de/quartznet15x5_de.csv
diff --git a/docs/source/asr/data/scores/en/citrinet_en.csv b/docs/source/asr/data/scores/en/citrinet_en.csv
diff --git a/docs/source/asr/data/scores/en/contextnet_en.csv b/docs/source/asr/data/scores/en/contextnet_en.csv
diff --git a/docs/source/asr/data/scores/en/jasper10x5dr_en.csv b/docs/source/asr/data/scores/en/jasper10x5dr_en.csv
diff --git a/docs/source/asr/data/scores/en/quartznet15x5_en.csv b/docs/source/asr/data/scores/en/quartznet15x5_en.csv
diff --git a/docs/source/asr/data/scores/en/squeezeformer_en.csv b/docs/source/asr/data/scores/en/squeezeformer_en.csv
diff --git a/docs/source/asr/data/scores/enes/contextnet_enes.csv b/docs/source/asr/data/scores/enes/contextnet_enes.csv
diff --git a/docs/source/asr/data/scores/es/citrinet_es.csv b/docs/source/asr/data/scores/es/citrinet_es.csv
diff --git a/docs/source/asr/data/scores/es/contextnet_es.csv b/docs/source/asr/data/scores/es/contextnet_es.csv