wehub/nvidia-nemo--speech
1
0
Fork 0
Code Issues Pull Requests Actions 192 Deployments Models Agent Notes Packages Projects Releases Wiki Activity
Files
main
nvidia-nemo--speech/docs/source/asr/api.rst
T
wehub-resource-sync ba4be087d5
CICD NeMo / cicd-main-unit-tests (push) Blocked by required conditions
Details
CICD NeMo / cicd-main-speech (push) Blocked by required conditions
Details
CICD NeMo / cicd-test-container-build (push) Blocked by required conditions
Details
CICD NeMo / cicd-import-tests (push) Blocked by required conditions
Details
CICD NeMo / L0_Setup_Test_Data_And_Models (push) Blocked by required conditions
Details
CICD NeMo / Nemo_CICD_Test (push) Blocked by required conditions
Details
CICD NeMo / Coverage (e2e) (push) Blocked by required conditions
Details
CICD NeMo / Coverage (unit-test) (push) Blocked by required conditions
Details
CodeQL / Analyze (python) (push) Waiting to run
Details
Create PR to main with cherry-pick from release / cherry-pick (push) Failing after 0s
Details
CICD NeMo / pre-flight (push) Failing after 0s
Details
CICD NeMo / configure (push) Has been skipped
Details
Build, validate, and release Neural Modules / pre-flight (push) Failing after 1s
Details
CICD NeMo / code-linting (push) Has been skipped
Details
CICD NeMo / cicd-wait-in-queue (push) Waiting to run
Details
Build, validate, and release Neural Modules / release (push) Has been skipped
Details
Build, validate, and release Neural Modules / release-summary (push) Has been cancelled
Details
chore: import upstream snapshot with attribution
2026-07-13 13:28:58 +08:00

368 lines
10 KiB
ReStructuredText
Raw Permalink Blame History

NeMo ASR API
============
Model Classes
-------------
.. autoclass:: nemo.collections.asr.models.EncDecCTCModel
:show-inheritance:
:members: transcribe, change_vocabulary, setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. autoclass:: nemo.collections.asr.models.EncDecCTCModelBPE
:show-inheritance:
:members: transcribe, change_vocabulary, setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. autoclass:: nemo.collections.asr.models.EncDecRNNTModel
:show-inheritance:
:members: transcribe, change_vocabulary, setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. autoclass:: nemo.collections.asr.models.EncDecRNNTBPEModel
:show-inheritance:
:members: transcribe, change_vocabulary, setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. autoclass:: nemo.collections.asr.models.EncDecRNNTBPEModelWithPrompt
:show-inheritance:
:members: transcribe, set_inference_prompt, initialize_prompt_feature, change_vocabulary, setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. autoclass:: nemo.collections.asr.models.EncDecHybridRNNTCTCBPEModelWithPrompt
:show-inheritance:
:members: transcribe, set_inference_prompt, initialize_prompt_feature, change_vocabulary, setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. autoclass:: nemo.collections.asr.models.EncDecMultiTalkerRNNTBPEModel
:show-inheritance:
:members: transcribe, change_vocabulary, setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. autoclass:: nemo.collections.asr.models.EncDecClassificationModel
:show-inheritance:
:members: setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. autoclass:: nemo.collections.asr.models.EncDecSpeakerLabelModel
:show-inheritance:
:members: setup_training_data, setup_optimization, setup_validation_data, setup_test_data, register_artifact
.. _asr-api-modules:
Modules
-------
.. autoclass:: nemo.collections.asr.modules.ConvASREncoder
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.modules.ConvASRDecoder
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.modules.ConvASRDecoderClassification
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.modules.SpeakerDecoder
:show-inheritance:
:members:
.. _conformer-encoder-api:
.. autoclass:: nemo.collections.asr.modules.ConformerEncoder
:show-inheritance:
:members:
.. _rnn-encoder-api:
.. autoclass:: nemo.collections.asr.modules.RNNEncoder
:show-inheritance:
:members:
.. _rnnt-decoder-api:
.. autoclass:: nemo.collections.asr.modules.RNNTDecoder
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.modules.StatelessTransducerDecoder
:show-inheritance:
:members:
.. _rnnt-joint-api:
.. autoclass:: nemo.collections.asr.modules.RNNTJoint
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.modules.SampledRNNTJoint
:show-inheritance:
:members:
Mixins
------
.. autoclass:: nemo.collections.asr.parts.mixins.mixins.ASRBPEMixin
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.mixins.mixins.ASRModuleMixin
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.mixins.transcription.TranscriptionMixin
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.mixins.transcription.TranscribeConfig
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.mixins.interctc_mixin.InterCTCMixin
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.mixins.multitalker_asr_mixins.SpeakerKernelMixin
:show-inheritance:
:members:
.. _asr-api-datasets:
Datasets
--------
Character Encoding Datasets
~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.data.audio_to_text.AudioToCharDataset
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.data.audio_to_text.TarredAudioToCharDataset
:show-inheritance:
:members:
Text-to-Text Datasets
~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.data.text_to_text.TextToTextDataset
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.data.text_to_text.TextToTextIterableDataset
:show-inheritance:
:members:
Speaker-Tagged Datasets for Multitalker ASR models
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.data.audio_to_text_lhotse_speaker.LhotseSpeechToTextSpkBpeDataset
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.data.audio_to_diar_label_lhotse.LhotseAudioToSpeechE2ESpkDiarDataset
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.data.data_simulation.MultiSpeakerSimulator
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.data.data_simulation.RIRMultiSpeakerSimulator
:show-inheritance:
:members:
Subword Encoding Datasets
~~~~~~~~~~~~~~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.data.audio_to_text.AudioToBPEDataset
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.data.audio_to_text.TarredAudioToBPEDataset
:show-inheritance:
:members:
.. _asr-audio-preprocessors:
Audio Preprocessors
-------------------
.. autoclass:: nemo.collections.asr.modules.AudioToMelSpectrogramPreprocessor
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.modules.AudioToMFCCPreprocessor
:show-inheritance:
:members:
.. _asr-api-audio-augmentors:
Audio Augmentors
----------------
.. autoclass:: nemo.collections.asr.modules.SpectrogramAugmentation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.modules.CropOrPadSpectrogramAugmentation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.SpeedPerturbation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.TimeStretchPerturbation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.GainPerturbation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.ImpulsePerturbation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.ShiftPerturbation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.NoisePerturbation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.WhiteNoisePerturbation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.RirAndNoisePerturbation
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.preprocessing.perturb.TranscodePerturbation
:show-inheritance:
:members:
Miscellaneous Classes
---------------------
CTC Decoding
~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.parts.submodules.ctc_decoding.CTCDecoding
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.ctc_decoding.CTCBPEDecoding
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.ctc_greedy_decoding.GreedyCTCInfer
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.ctc_beam_decoding.BeamCTCInfer
:show-inheritance:
:members:
RNNT Decoding
~~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.parts.submodules.rnnt_decoding.RNNTDecoding
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.rnnt_decoding.RNNTBPEDecoding
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.rnnt_greedy_decoding.GreedyRNNTInfer
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.rnnt_greedy_decoding.GreedyBatchedRNNTInfer
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.rnnt_beam_decoding.BeamRNNTInfer
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.rnnt_beam_decoding.BeamBatchedRNNTInfer
:show-inheritance:
:members:
TDT Decoding
~~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.parts.submodules.rnnt_greedy_decoding.GreedyTDTInfer
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.rnnt_greedy_decoding.GreedyBatchedTDTInfer
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.tdt_beam_decoding.BeamTDTInfer
:show-inheritance:
:members:
.. autoclass:: nemo.collections.asr.parts.submodules.tdt_beam_decoding.BeamBatchedTDTInfer
:show-inheritance:
:members:
Hypotheses
~~~~~~~~~~
.. autoclass:: nemo.collections.asr.parts.utils.rnnt_utils.Hypothesis
:show-inheritance:
:no-members:
.. autoclass:: nemo.collections.asr.parts.utils.rnnt_utils.NBestHypotheses
:show-inheritance:
:no-members:
Adapter Networks
~~~~~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.parts.submodules.adapters.multi_head_attention_adapter_module.MultiHeadAttentionAdapter
:show-inheritance:
:members:
:member-order: bysource
.. autoclass:: nemo.collections.asr.parts.submodules.adapters.multi_head_attention_adapter_module.RelPositionMultiHeadAttentionAdapter
:show-inheritance:
:members:
:member-order: bysource
.. autoclass:: nemo.collections.asr.parts.submodules.adapters.multi_head_attention_adapter_module.PositionalEncodingAdapter
:show-inheritance:
:members:
:member-order: bysource
.. autoclass:: nemo.collections.asr.parts.submodules.adapters.multi_head_attention_adapter_module.RelPositionalEncodingAdapter
:show-inheritance:
:members:
:member-order: bysource
Adapter Strategies
~~~~~~~~~~~~~~~~~~
.. autoclass:: nemo.collections.asr.parts.submodules.adapters.multi_head_attention_adapter_module.MHAResidualAddAdapterStrategy
:show-inheritance:
:members:
:member-order: bysource
:undoc-members: adapter_module_names
Reference in New Issue View Git Blame Copy Permalink