Transformation stage 0: NeMo docs revision

docs/false_positives.json

@@ -1,11 +1,3 @@
-{
-  "filename": "nlp/text_normalization/nn_text_normalization.rst",
-  "lineno": 247,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://research.fb.com/wp-content/uploads/2019/03/Neural-Models-of-Text-Normalization-for-Speech-Applications.pdf",
-  "info": "400 Client Error: Bad Request for url: https://research.facebook.com/wp-content/uploads/2019/03/Neural-Models-of-Text-Normalization-for-Speech-Applications.pdf"
-}
 {
   "filename": "asr/api.rst",
   "lineno": 7,
@@ -22,86 +14,6 @@
   "uri": "https://github.com/NVIDIA/NeMo/blob/main/nemo/collections/asr/modules/hybrid_autoregressive_transducer.py#L39",
   "info": "Anchor 'L39' not found"
 }
-{
-  "filename": "nlp/bert_pretraining.rst",
-  "lineno": 53,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/LanguageModeling/BERT#quick-start-guide",
-  "info": "Anchor 'quick-start-guide' not found"
-}
-{
-  "filename": "nlp/text_normalization/wfst/wfst_customization.rst",
-  "lineno": 17,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/NeMo-text-processing#from-source",
-  "info": "Anchor 'from-source' not found"
-}
-{
-  "filename": "nlp/nemo_megatron/gpt/gpt_training.rst",
-  "lineno": 115,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/NeMo/blob/main/examples/llm/pretrain/README.md#run-pre-training-with-a-default-recipe",
-  "info": "Anchor 'run-pre-training-with-a-default-recipe' not found"
-}
-{
-  "filename": "nlp/nemo_megatron/gpt/gpt_training.rst",
-  "lineno": 115,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/NeMo/blob/main/examples/llm/pretrain/README.md#create-and-run-a-custom-recipe",
-  "info": "Anchor 'create-and-run-a-custom-recipe' not found"
-}
-{
-  "filename": "nlp/joint_intent_slot.rst",
-  "lineno": 155,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/NeMo/blob/stable/docs/source/nlp/nlp_model.rst#model-nlp",
-  "info": "Anchor 'model-nlp' not found"
-}
-{
-  "filename": "nlp/machine_translation/machine_translation.rst",
-  "lineno": 242,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/NeMo/blob/v1.0.2/nemo/collections/nlp/data/machine_translation/machine_translation_dataset.py#L67",
-  "info": "Anchor 'L67' not found"
-}
-{
-  "filename": "nlp/punctuation_and_capitalization_lexical_audio.rst",
-  "lineno": 255,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/NeMo/tree/stable/nemo/collections/common/parts/adapter_modules.py#L157",
-  "info": "Anchor 'L157' not found"
-}
-{
-  "filename": "nlp/question_answering.rst",
-  "lineno": 196,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://msmarco.blob.core.windows.net/msmarco/dev_v2.1.json.gz",
-  "info": "409 Client Error: Public access is not permitted on this storage account. for url: https://msmarco.blob.core.windows.net/msmarco/dev_v2.1.json.gz"
-}
-{
-  "filename": "nlp/question_answering.rst",
-  "lineno": 195,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://msmarco.blob.core.windows.net/msmarco/train_v2.1.json.gz",
-  "info": "409 Client Error: Public access is not permitted on this storage account. for url: https://msmarco.blob.core.windows.net/msmarco/train_v2.1.json.gz"
-}
-{
-  "filename": "nlp/language_modeling.rst",
-  "lineno": 54,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/NeMo/tree/stable/nemo/collections/nlp/data/language_modeling/sentence_dataset.py#L35",
-  "info": "Anchor 'L35' not found"
-}
 {
   "filename": "features/optimizations/activation_recomputation.rst",
   "lineno": 12,
@@ -142,14 +54,6 @@
   "uri": "https://github.com/NVIDIA/Megatron-LM/blob/e2ec14ab5690fead7e33760b0f8fb20c83b4fd1f/megatron/core/transformer/moe/moe_layer.py#L29",
   "info": "Anchor 'L29' not found"
 }
-{
-  "filename": "nlp/spellchecking_asr_customization.rst",
-  "lineno": 38,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/NeMo/blob/stable/tutorials/nlp/SpellMapper_English_ASR_Customization.ipynb",
-  "info": "404 Client Error: Not Found for url: https://github.com/NVIDIA/NeMo/blob/stable/tutorials/nlp/SpellMapper_English_ASR_Customization.ipynb"
-}
 {
   "filename": "tools/nemo_forced_aligner.rst",
   "lineno": 16,
@@ -166,40 +70,3 @@
   "uri": "https://nvidia.github.io/NeMo/blogs/2023/2023-08-forced-alignment/",
   "info": "404 Client Error: Not Found for url: https://nvidia.github.io/NeMo/blogs/2023/2023-08-forced-alignment/"
 }
-{
-  "filename": "nlp/text_normalization/wfst/wfst_text_processing_deployment.rst",
-  "lineno": 10,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://www.openfst.org/",
-  "info": "HTTPSConnectionPool(host='www.openfst.org', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))"
-}
-{
-  "filename": "nlp/text_normalization/wfst/wfst_text_processing_deployment.rst",
-  "lineno": 76,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://www.openfst.org/twiki/bin/view/GRM/Thrax",
-  "info": "HTTPSConnectionPool(host='www.openfst.org', port=443): Max retries exceeded with url: /twiki/bin/view/GRM/Thrax (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))"
-  "lineno": 76,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://www.openfst.org/twiki/bin/view/GRM/Thrax",
-  "info": "HTTPSConnectionPool(host='www.openfst.org', port=443): Max retries exceeded with url: /twiki/bin/view/GRM/Thrax (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))"
-}
-{
-  "filename": "nlp/text_normalization/wfst/wfst_text_processing_deployment.rst",
-  "lineno": 10,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://www.openfst.org/",
-  "info": "HTTPSConnectionPool(host='www.openfst.org', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1016)')))"
-}
-{
-  "filename": "nlp/text_normalization/wfst/wfst_customization.rst",
-  "lineno": 11,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://www.opengrm.org/twiki/bin/view/GRM/Pynini",
-  "info": "403 Client Error: Forbidden for url: https://www.opengrm.org/twiki/bin/view/GRM/Pynini"
-}

docs/links_needing_review.json

@@ -1,107 +1,3 @@
-{
-  "filename": "multimodal/nerf/configs.rst",
-  "lineno": 4,
-  "status": "broken",
-  "code": 0,
-  "uri": "../../core/core.html",
-  "info": ""
-}
-{
-  "filename": "multimodal/vlm/configs.rst",
-  "lineno": 160,
-  "status": "broken",
-  "code": 0,
-  "uri": "./clip.html#clip",
-  "info": ""
-}
-{
-  "filename": "multimodal/text2img/configs.rst",
-  "lineno": 51,
-  "status": "broken",
-  "code": 0,
-  "uri": "./datasets.html",
-  "info": ""
-}
-{
-  "filename": "multimodal/nerf/configs.rst",
-  "lineno": 80,
-  "status": "broken",
-  "code": 0,
-  "uri": "./datasets.html#Datasets",
-  "info": ""
-}
-{
-  "filename": "multimodal/nerf/configs.rst",
-  "lineno": 125,
-  "status": "broken",
-  "code": 0,
-  "uri": "./dreamfusion.html#dreamfusion",
-  "info": ""
-}
-{
-  "filename": "vision/configs.rst",
-  "lineno": 133,
-  "status": "broken",
-  "code": 0,
-  "uri": "./vit.html#vit",
-  "info": ""
-}
-{
-  "filename": "multimodal/text2img/configs.rst",
-  "lineno": 12,
-  "status": "broken",
-  "code": 0,
-  "uri": "PUTTHEURL",
-  "info": ""
-}
-{
-  "filename": "multimodal/mllm/configs.rst",
-  "lineno": 143,
-  "status": "broken",
-  "code": 0,
-  "uri": "./neva.html#neva",
-  "info": ""
-}
-{
-  "filename": "multimodal/text2img/datasets.rst",
-  "lineno": 32,
-  "status": "broken",
-  "code": 0,
-  "uri": "http://TODOURL",
-  "info": "HTTPConnectionPool(host='todourl', port=80): Max retries exceeded with url: / (Caused by NameResolutionError(\"<urllib3.connection.HTTPConnection object at 0x10fe3a270>: Failed to resolve 'todourl' ([Errno 8] nodename nor servname provided, or not known)\"))"
-}
-{
-  "filename": "multimodal/mllm/datasets.rst",
-  "lineno": 29,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://cocodataset.org/#download",
-  "info": "Anchor 'download' not found"
-}
-{
-  "filename": "multimodal/mllm/intro.rst",
-  "lineno": 4,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://docs.nvidia.com/nemo-framework/user-guide/latest/multimodalmodels/index.html",
-  "info": "404 Client Error: Not Found for url: https://docs.nvidia.com/nemo-framework/user-guide/latest/multimodalmodels/index.html"
-}
-{
-  "filename": "multimodal/vlm/clip.rst",
-  "lineno": 140,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/Megatron-LM#distributed-optimizer",
-  "info": "Anchor 'distributed-optimizer' not found"
-}
-{
-  "filename": "multimodal/mllm/neva.rst",
-  "lineno": 132,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/NVIDIA/Megatron-LM#distributed-pretraining",
-  "info": "Anchor 'distributed-pretraining' not found"
-}
 {
   "filename": "checkpoints/dist_ckpt.rst",
   "lineno": 428,
@@ -118,22 +14,6 @@
   "uri": "https://github.com/NVIDIA/NeMo#installation",
   "info": "Anchor 'installation' not found"
 }
-{
-  "filename": "multimodal/text2img/insp2p.rst",
-  "lineno": 16,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/timothybrooks/instruct-pix2pix#generated-dataset",
-  "info": "Anchor 'generated-dataset' not found"
-}
-{
-  "filename": "multimodal/text2img/configs.rst",
-  "lineno": 51,
-  "status": "broken",
-  "code": 0,
-  "uri": "https://github.com/webdataset/webdataset#multinode-training",
-  "info": "Anchor 'multinode-training' not found"
-}
 {
   "filename": "checkpoints/intro.rst",
   "lineno": 28,
@@ -142,14 +22,6 @@
   "uri": "https://nvidia.github.io/TensorRT-LLM/architecture/checkpoint.html",
   "info": "404 Client Error: Not Found for url: https://nvidia.github.io/TensorRT-LLM/architecture/checkpoint.html"
 }
-{
-  "filename": "multimodal/text2img/configs.rst",
-  "lineno": 23,
-  "status": "broken",
-  "code": 0,
-  "uri": "../api.html#Datasets",
-  "info": ""
-}
 {
   "filename": "audio/configs.rst",
   "lineno": 17,

docs/source/apis.rst

@@ -2,11 +2,9 @@
 NeMo APIs
 =========
 
-**NOTE: This page is intended for NeMo 1.0 features only.**
-
 You can learn more about the underlying principles of the NeMo codebase in this section.
 
-The `NeMo Framework codebase <https://github.com/NVIDIA/NeMo>`__ is composed of a `core <https://github.com/NVIDIA/NeMo/tree/main/nemo/core>`__ section which contains the main building blocks of the framework, and various `collections <https://github.com/NVIDIA/NeMo/tree/main/nemo/collections>`__ which help you
+The `NeMo Toolkit codebase <https://github.com/NVIDIA/NeMo>`__ is composed of a `core <https://github.com/NVIDIA/NeMo/tree/main/nemo/core>`__ section which contains the main building blocks of the framework, and various `collections <https://github.com/NVIDIA/NeMo/tree/main/nemo/collections>`__ which help you
 build specialized AI models.
 
 You can learn more about aspects of the NeMo "core" by following the links below:
@@ -20,7 +18,6 @@ You can learn more about aspects of the NeMo "core" by following the links below
    core/neural_modules
    core/exp_manager
    core/neural_types
-   core/export
    core/adapters/intro
 
 You can learn more about aspects of the NeMo APIs by following the links below:
@@ -34,6 +31,7 @@ You can learn more about aspects of the NeMo APIs by following the links below:
    common/intro
    asr/api
    tts/api
+   audio/api
 
 
 Alternatively, you can jump straight to the documentation for the individual collections:
@@ -42,3 +40,7 @@ Alternatively, you can jump straight to the documentation for the individual col
 
 * :doc:`Text-to-Speech (TTS) <../tts/intro>`
 
+* :doc:`Audio Processing <../audio/intro>`
+
+* :doc:`SpeechLM2 <../speechlm2/intro>`
+

docs/source/asr/all_chkpt.rst

@@ -47,6 +47,7 @@ Arabic
    :align: left
    :widths: 50,50
    :header-rows: 1
+
 ------------------------------
 
 Russian
@@ -66,10 +67,11 @@ Portuguese
    :align: left
    :widths: 50,50
    :header-rows: 1
+
 -----------------------------
 
 Belarusian
-^^^^^^^
+^^^^^^^^^^
 .. csv-table::
    :file: data/benchmark_be.csv
    :align: left
@@ -89,7 +91,7 @@ Japanese
 -----------------------------
 
 Armenian
-^^^^^^^
+^^^^^^^^
 .. csv-table::
    :file: data/benchmark_hy.csv
    :align: left

docs/source/asr/asr_language_modeling_and_customization.rst

@@ -66,4 +66,15 @@ LM Training
 -----------
 
 NeMo provides tools for training n-gram language models that can be used for language model fusion or word-boosting.
-For details, please refer to: :ref:`ngram-utils`.
+For details, please refer to: :ref:`ngram-utils`.
+
+
+.. toctree::
+   :maxdepth: 1
+   :hidden:
+
+   asr_customization/ngpulm_language_modeling_and_customization
+   asr_customization/neural_rescoring
+   asr_customization/legacy_language_modeling_and_customization
+   asr_customization/ngram_utils
+   asr_customization/word_boosting

docs/source/asr/datasets.rst

@@ -670,6 +670,8 @@ Some other Lhotse related arguments we support:
 
 The full and always up-to-date list of supported options can be found in ``LhotseDataLoadingConfig`` class.
 
+.. _asr-dataset-config-format:
+
 Extended multi-dataset configuration format
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~