- en: torchaudio.prototype
  id: totrans-0
  prefs:
  - PREF_H1
  type: TYPE_NORMAL
  zh: torchaudio.prototype
- en: 原文：[https://pytorch.org/audio/stable/prototype.html](https://pytorch.org/audio/stable/prototype.html)
  id: totrans-1
  prefs:
  - PREF_BQ
  type: TYPE_NORMAL
  zh: '[https://pytorch.org/audio/stable/prototype.html](https://pytorch.org/audio/stable/prototype.html)'
- en: '`torchaudio.prototype` provides prototype features; they are at an early stage
    for feedback and testing. Their interfaces might be changed without prior notice.'
  id: totrans-2
  prefs: []
  type: TYPE_NORMAL
  zh: '`torchaudio.prototype`提供原型功能；它们处于早期阶段，用于反馈和测试。它们的接口可能会在没有事先通知的情况下更改。'
- en: Most modules of prototypes are excluded from release. Please refer to [here](https://pytorch.org/audio)
    for more information on prototype features.
  id: totrans-3
  prefs: []
  type: TYPE_NORMAL
  zh: 原型的大多数模块都不包含在发布中。请参考[这里](https://pytorch.org/audio)获取有关原型功能的更多信息。
- en: The modules under `torchaudio.prototype` must be imported explicitly, e.g.
  id: totrans-4
  prefs: []
  type: TYPE_NORMAL
  zh: '`torchaudio.prototype`模块必须显式导入，例如'
- en: '[PRE0]'
  id: totrans-5
  prefs: []
  type: TYPE_PRE
  zh: '[PRE0]'
- en: '[torchaudio.prototype.datasets](prototype.datasets.html)'
  id: totrans-6
  prefs:
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.datasets](prototype.datasets.html)'
- en: '[Musan](generated/torchaudio.prototype.datasets.Musan.html)'
  id: totrans-7
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Musan](generated/torchaudio.prototype.datasets.Musan.html)'
- en: '[__getitem__](generated/torchaudio.prototype.datasets.Musan.html#getitem)'
  id: totrans-8
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[__getitem__](generated/torchaudio.prototype.datasets.Musan.html#getitem)'
- en: '[get_metadata](generated/torchaudio.prototype.datasets.Musan.html#get-metadata)'
  id: totrans-9
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[get_metadata](generated/torchaudio.prototype.datasets.Musan.html#get-metadata)'
- en: '[torchaudio.prototype.functional](prototype.functional.html)'
  id: totrans-10
  prefs:
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional](prototype.functional.html)'
- en: '[Utility](prototype.functional.html#utility)'
  id: totrans-11
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Utility](prototype.functional.html#utility)'
- en: '[torchaudio.prototype.functional.barkscale_fbanks](generated/torchaudio.prototype.functional.barkscale_fbanks.html)'
  id: totrans-12
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.barkscale_fbanks](generated/torchaudio.prototype.functional.barkscale_fbanks.html)'
- en: '[torchaudio.prototype.functional.chroma_filterbank](generated/torchaudio.prototype.functional.chroma_filterbank.html)'
  id: totrans-13
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.chroma_filterbank](generated/torchaudio.prototype.functional.chroma_filterbank.html)'
- en: '[DSP](prototype.functional.html#dsp)'
  id: totrans-14
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[DSP](prototype.functional.html#dsp)'
- en: '[torchaudio.prototype.functional.adsr_envelope](generated/torchaudio.prototype.functional.adsr_envelope.html)'
  id: totrans-15
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.adsr_envelope](generated/torchaudio.prototype.functional.adsr_envelope.html)'
- en: '[torchaudio.prototype.functional.filter_waveform](generated/torchaudio.prototype.functional.filter_waveform.html)'
  id: totrans-16
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.filter_waveform](generated/torchaudio.prototype.functional.filter_waveform.html)'
- en: '[torchaudio.prototype.functional.extend_pitch](generated/torchaudio.prototype.functional.extend_pitch.html)'
  id: totrans-17
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.extend_pitch](generated/torchaudio.prototype.functional.extend_pitch.html)'
- en: '[torchaudio.prototype.functional.oscillator_bank](generated/torchaudio.prototype.functional.oscillator_bank.html)'
  id: totrans-18
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.oscillator_bank](generated/torchaudio.prototype.functional.oscillator_bank.html)'
- en: '[torchaudio.prototype.functional.sinc_impulse_response](generated/torchaudio.prototype.functional.sinc_impulse_response.html)'
  id: totrans-19
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.sinc_impulse_response](generated/torchaudio.prototype.functional.sinc_impulse_response.html)'
- en: '[torchaudio.prototype.functional.frequency_impulse_response](generated/torchaudio.prototype.functional.frequency_impulse_response.html)'
  id: totrans-20
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.frequency_impulse_response](generated/torchaudio.prototype.functional.frequency_impulse_response.html)'
- en: '[Room Impulse Response Simulation](prototype.functional.html#room-impulse-response-simulation)'
  id: totrans-21
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Room Impulse Response Simulation](prototype.functional.html#room-impulse-response-simulation)'
- en: '[torchaudio.prototype.functional.ray_tracing](generated/torchaudio.prototype.functional.ray_tracing.html)'
  id: totrans-22
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.ray_tracing](generated/torchaudio.prototype.functional.ray_tracing.html)'
- en: '[torchaudio.prototype.functional.simulate_rir_ism](generated/torchaudio.prototype.functional.simulate_rir_ism.html)'
  id: totrans-23
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.functional.simulate_rir_ism](generated/torchaudio.prototype.functional.simulate_rir_ism.html)'
- en: '[torchaudio.prototype.models](prototype.models.html)'
  id: totrans-24
  prefs:
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models](prototype.models.html)'
- en: '[ConformerWav2Vec2PretrainModel](generated/torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.html)'
  id: totrans-25
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[ConformerWav2Vec2PretrainModel](generated/torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.html)'
- en: '[Methods](generated/torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.html#methods)'
  id: totrans-26
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Methods](generated/torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.html#methods)'
- en: '[forward](generated/torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.html#forward)'
  id: totrans-27
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[forward](generated/torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.html#forward)'
- en: '[Factory Functions](generated/torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.html#factory-functions)'
  id: totrans-28
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Factory Functions](generated/torchaudio.prototype.models.ConformerWav2Vec2PretrainModel.html#factory-functions)'
- en: '[torchaudio.prototype.models.conformer_wav2vec2_pretrain_model](generated/torchaudio.prototype.models.conformer_wav2vec2_pretrain_model.html)'
  id: totrans-29
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.conformer_wav2vec2_pretrain_model](generated/torchaudio.prototype.models.conformer_wav2vec2_pretrain_model.html)'
- en: '[torchaudio.prototype.models.conformer_wav2vec2_pretrain_base](generated/torchaudio.prototype.models.conformer_wav2vec2_pretrain_base.html)'
  id: totrans-30
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.conformer_wav2vec2_pretrain_base](generated/torchaudio.prototype.models.conformer_wav2vec2_pretrain_base.html)'
- en: '[torchaudio.prototype.models.conformer_wav2vec2_pretrain_large](generated/torchaudio.prototype.models.conformer_wav2vec2_pretrain_large.html)'
  id: totrans-31
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.conformer_wav2vec2_pretrain_large](generated/torchaudio.prototype.models.conformer_wav2vec2_pretrain_large.html)'
- en: '[ConvEmformer](generated/torchaudio.prototype.models.ConvEmformer.html)'
  id: totrans-32
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[ConvEmformer](generated/torchaudio.prototype.models.ConvEmformer.html)'
- en: '[Methods](generated/torchaudio.prototype.models.ConvEmformer.html#methods)'
  id: totrans-33
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Methods](generated/torchaudio.prototype.models.ConvEmformer.html#methods)'
- en: '[forward](generated/torchaudio.prototype.models.ConvEmformer.html#forward)'
  id: totrans-34
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[forward](generated/torchaudio.prototype.models.ConvEmformer.html#forward)'
- en: '[infer](generated/torchaudio.prototype.models.ConvEmformer.html#infer)'
  id: totrans-35
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[infer](generated/torchaudio.prototype.models.ConvEmformer.html#infer)'
- en: '[HiFiGANVocoder](generated/torchaudio.prototype.models.HiFiGANVocoder.html)'
  id: totrans-36
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[HiFiGANVocoder](generated/torchaudio.prototype.models.HiFiGANVocoder.html)'
- en: '[Methods](generated/torchaudio.prototype.models.HiFiGANVocoder.html#methods)'
  id: totrans-37
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Methods](generated/torchaudio.prototype.models.HiFiGANVocoder.html#methods)'
- en: '[forward](generated/torchaudio.prototype.models.HiFiGANVocoder.html#forward)'
  id: totrans-38
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[forward](generated/torchaudio.prototype.models.HiFiGANVocoder.html#forward)'
- en: '[Factory Functions](generated/torchaudio.prototype.models.HiFiGANVocoder.html#factory-functions)'
  id: totrans-39
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Factory Functions](generated/torchaudio.prototype.models.HiFiGANVocoder.html#factory-functions)'
- en: '[torchaudio.prototype.models.hifigan_vocoder](generated/torchaudio.prototype.models.hifigan_vocoder.html)'
  id: totrans-40
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.hifigan_vocoder](generated/torchaudio.prototype.models.hifigan_vocoder.html)'
- en: '[torchaudio.prototype.models.hifigan_vocoder_v1](generated/torchaudio.prototype.models.hifigan_vocoder_v1.html)'
  id: totrans-41
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.hifigan_vocoder_v1](generated/torchaudio.prototype.models.hifigan_vocoder_v1.html)'
- en: '[torchaudio.prototype.models.hifigan_vocoder_v2](generated/torchaudio.prototype.models.hifigan_vocoder_v2.html)'
  id: totrans-42
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.hifigan_vocoder_v2](generated/torchaudio.prototype.models.hifigan_vocoder_v2.html)'
- en: '[torchaudio.prototype.models.hifigan_vocoder_v3](generated/torchaudio.prototype.models.hifigan_vocoder_v3.html)'
  id: totrans-43
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.hifigan_vocoder_v3](generated/torchaudio.prototype.models.hifigan_vocoder_v3.html)'
- en: '[Prototype Factory Functions of Beta Models](prototype.models.html#prototype-factory-functions-of-beta-models)'
  id: totrans-44
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Prototype Factory Functions of Beta Models](prototype.models.html#prototype-factory-functions-of-beta-models)'
- en: '[Wav2Vec2Model](generated/torchaudio.models.Wav2Vec2Model.html)'
  id: totrans-45
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Wav2Vec2Model](generated/torchaudio.models.Wav2Vec2Model.html)'
- en: '[Methods](generated/torchaudio.models.Wav2Vec2Model.html#methods)'
  id: totrans-46
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Methods](generated/torchaudio.models.Wav2Vec2Model.html#methods)'
- en: '[forward](generated/torchaudio.models.Wav2Vec2Model.html#forward)'
  id: totrans-47
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[forward](generated/torchaudio.models.Wav2Vec2Model.html#forward)'
- en: '[extract_features](generated/torchaudio.models.Wav2Vec2Model.html#extract-features)'
  id: totrans-48
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[extract_features](generated/torchaudio.models.Wav2Vec2Model.html#extract-features)'
- en: '[Factory Functions](generated/torchaudio.models.Wav2Vec2Model.html#factory-functions)'
  id: totrans-49
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Factory Functions](generated/torchaudio.models.Wav2Vec2Model.html#factory-functions)'
- en: '[torchaudio.models.wav2vec2_model](generated/torchaudio.models.wav2vec2_model.html)'
  id: totrans-50
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2_model](generated/torchaudio.models.wav2vec2_model.html)'
- en: '[torchaudio.models.wav2vec2_base](generated/torchaudio.models.wav2vec2_base.html)'
  id: totrans-51
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2_base](generated/torchaudio.models.wav2vec2_base.html)'
- en: '[torchaudio.models.wav2vec2_large](generated/torchaudio.models.wav2vec2_large.html)'
  id: totrans-52
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2_large](generated/torchaudio.models.wav2vec2_large.html)'
- en: '[torchaudio.models.wav2vec2_large_lv60k](generated/torchaudio.models.wav2vec2_large_lv60k.html)'
  id: totrans-53
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2_large_lv60k](generated/torchaudio.models.wav2vec2_large_lv60k.html)'
- en: '[torchaudio.models.wav2vec2_xlsr_300m](generated/torchaudio.models.wav2vec2_xlsr_300m.html)'
  id: totrans-54
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2_xlsr_300m](generated/torchaudio.models.wav2vec2_xlsr_300m.html)'
- en: '[torchaudio.models.wav2vec2_xlsr_1b](generated/torchaudio.models.wav2vec2_xlsr_1b.html)'
  id: totrans-55
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2_xlsr_1b](generated/torchaudio.models.wav2vec2_xlsr_1b.html)'
- en: '[torchaudio.models.wav2vec2_xlsr_2b](generated/torchaudio.models.wav2vec2_xlsr_2b.html)'
  id: totrans-56
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2_xlsr_2b](generated/torchaudio.models.wav2vec2_xlsr_2b.html)'
- en: '[torchaudio.models.hubert_base](generated/torchaudio.models.hubert_base.html)'
  id: totrans-57
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.hubert_base](generated/torchaudio.models.hubert_base.html)'
- en: '[torchaudio.models.hubert_large](generated/torchaudio.models.hubert_large.html)'
  id: totrans-58
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.hubert_large](generated/torchaudio.models.hubert_large.html)'
- en: '[torchaudio.models.hubert_xlarge](generated/torchaudio.models.hubert_xlarge.html)'
  id: totrans-59
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.hubert_xlarge](generated/torchaudio.models.hubert_xlarge.html)'
- en: '[torchaudio.models.wavlm_model](generated/torchaudio.models.wavlm_model.html)'
  id: totrans-60
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wavlm_model](generated/torchaudio.models.wavlm_model.html)'
- en: '[torchaudio.models.wavlm_base](generated/torchaudio.models.wavlm_base.html)'
  id: totrans-61
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wavlm_base](generated/torchaudio.models.wavlm_base.html)'
- en: '[torchaudio.models.wavlm_large](generated/torchaudio.models.wavlm_large.html)'
  id: totrans-62
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wavlm_large](generated/torchaudio.models.wavlm_large.html)'
- en: '[Prototype Factory Functions](generated/torchaudio.models.Wav2Vec2Model.html#prototype-factory-functions)'
  id: totrans-63
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Prototype Factory Functions](generated/torchaudio.models.Wav2Vec2Model.html#prototype-factory-functions)'
- en: '[torchaudio.prototype.models.emformer_hubert_model](generated/torchaudio.prototype.models.emformer_hubert_model.html)'
  id: totrans-64
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.emformer_hubert_model](generated/torchaudio.prototype.models.emformer_hubert_model.html)'
- en: '[torchaudio.prototype.models.emformer_hubert_base](generated/torchaudio.prototype.models.emformer_hubert_base.html)'
  id: totrans-65
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.emformer_hubert_base](generated/torchaudio.prototype.models.emformer_hubert_base.html)'
- en: '[torchaudio.prototype.models.conformer_wav2vec2_model](generated/torchaudio.prototype.models.conformer_wav2vec2_model.html)'
  id: totrans-66
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.conformer_wav2vec2_model](generated/torchaudio.prototype.models.conformer_wav2vec2_model.html)'
- en: '[torchaudio.prototype.models.conformer_wav2vec2_base](generated/torchaudio.prototype.models.conformer_wav2vec2_base.html)'
  id: totrans-67
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.conformer_wav2vec2_base](generated/torchaudio.prototype.models.conformer_wav2vec2_base.html)'
- en: '[Utility Functions](generated/torchaudio.models.Wav2Vec2Model.html#utility-functions)'
  id: totrans-68
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Utility Functions](generated/torchaudio.models.Wav2Vec2Model.html#utility-functions)'
- en: '[torchaudio.models.wav2vec2.utils.import_fairseq_model](generated/torchaudio.models.wav2vec2.utils.import_fairseq_model.html)'
  id: totrans-69
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2.utils.import_fairseq_model](generated/torchaudio.models.wav2vec2.utils.import_fairseq_model.html)'
- en: '[torchaudio.models.wav2vec2.utils.import_huggingface_model](generated/torchaudio.models.wav2vec2.utils.import_huggingface_model.html)'
  id: totrans-70
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.wav2vec2.utils.import_huggingface_model](generated/torchaudio.models.wav2vec2.utils.import_huggingface_model.html)'
- en: '[RNNT](generated/torchaudio.models.RNNT.html)'
  id: totrans-71
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[RNNT](generated/torchaudio.models.RNNT.html)'
- en: '[Methods](generated/torchaudio.models.RNNT.html#methods)'
  id: totrans-72
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Methods](generated/torchaudio.models.RNNT.html#methods)'
- en: '[forward](generated/torchaudio.models.RNNT.html#forward)'
  id: totrans-73
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[forward](generated/torchaudio.models.RNNT.html#forward)'
- en: '[transcribe_streaming](generated/torchaudio.models.RNNT.html#transcribe-streaming)'
  id: totrans-74
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[transcribe_streaming](generated/torchaudio.models.RNNT.html#transcribe-streaming)'
- en: '[transcribe](generated/torchaudio.models.RNNT.html#transcribe)'
  id: totrans-75
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[transcribe](generated/torchaudio.models.RNNT.html#transcribe)'
- en: '[predict](generated/torchaudio.models.RNNT.html#predict)'
  id: totrans-76
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[predict](generated/torchaudio.models.RNNT.html#predict)'
- en: '[join](generated/torchaudio.models.RNNT.html#join)'
  id: totrans-77
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[join](generated/torchaudio.models.RNNT.html#join)'
- en: '[Factory Functions](generated/torchaudio.models.RNNT.html#factory-functions)'
  id: totrans-78
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Factory Functions](generated/torchaudio.models.RNNT.html#factory-functions)'
- en: '[torchaudio.models.emformer_rnnt_model](generated/torchaudio.models.emformer_rnnt_model.html)'
  id: totrans-79
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.emformer_rnnt_model](generated/torchaudio.models.emformer_rnnt_model.html)'
- en: '[torchaudio.models.emformer_rnnt_base](generated/torchaudio.models.emformer_rnnt_base.html)'
  id: totrans-80
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.models.emformer_rnnt_base](generated/torchaudio.models.emformer_rnnt_base.html)'
- en: '[Prototype Factory Functions](generated/torchaudio.models.RNNT.html#prototype-factory-functions)'
  id: totrans-81
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Prototype Factory Functions](generated/torchaudio.models.RNNT.html#prototype-factory-functions)'
- en: '[torchaudio.prototype.models.conformer_rnnt_model](generated/torchaudio.prototype.models.conformer_rnnt_model.html)'
  id: totrans-82
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.conformer_rnnt_model](generated/torchaudio.prototype.models.conformer_rnnt_model.html)'
- en: '[torchaudio.prototype.models.conformer_rnnt_base](generated/torchaudio.prototype.models.conformer_rnnt_base.html)'
  id: totrans-83
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.models.conformer_rnnt_base](generated/torchaudio.prototype.models.conformer_rnnt_base.html)'
- en: '[torchaudio.prototype.pipelines](prototype.pipelines.html)'
  id: totrans-84
  prefs:
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.pipelines](prototype.pipelines.html)'
- en: '[RNN-T Streaming/Non-Streaming ASR](prototype.pipelines.html#rnn-t-streaming-non-streaming-asr)'
  id: totrans-85
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[RNN-T Streaming/Non-Streaming ASR](prototype.pipelines.html#rnn-t-streaming-non-streaming-asr)'
- en: '[Pretrained Models](prototype.pipelines.html#pretrained-models)'
  id: totrans-86
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[Pretrained Models](prototype.pipelines.html#pretrained-models)'
- en: '[EMFORMER_RNNT_BASE_MUSTC](generated/torchaudio.prototype.pipelines.EMFORMER_RNNT_BASE_MUSTC.html)'
  id: totrans-87
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[EMFORMER_RNNT_BASE_MUSTC](generated/torchaudio.prototype.pipelines.EMFORMER_RNNT_BASE_MUSTC.html)'
- en: '[EMFORMER_RNNT_BASE_TEDLIUM3](generated/torchaudio.prototype.pipelines.EMFORMER_RNNT_BASE_TEDLIUM3.html)'
  id: totrans-88
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[EMFORMER_RNNT_BASE_TEDLIUM3](generated/torchaudio.prototype.pipelines.EMFORMER_RNNT_BASE_TEDLIUM3.html)'
- en: '[HiFiGAN Vocoder](prototype.pipelines.html#hifigan-vocoder)'
  id: totrans-89
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[HiFiGAN 语音合成器](prototype.pipelines.html#hifigan-vocoder)'
- en: '[Interface](prototype.pipelines.html#interface)'
  id: totrans-90
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[接口](prototype.pipelines.html#interface)'
- en: '[HiFiGANVocoderBundle](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html)'
  id: totrans-91
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[HiFiGANVocoderBundle](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html)'
- en: '[Properties](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#properties)'
  id: totrans-92
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[属性](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#properties)'
- en: '[sample_rate](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#sample-rate)'
  id: totrans-93
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[采样率](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#sample-rate)'
- en: '[Methods](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#methods)'
  id: totrans-94
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[方法](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#methods)'
- en: '[get_mel_transform](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#get-mel-transform)'
  id: totrans-95
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[获取梅尔变换](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#get-mel-transform)'
- en: '[get_vocoder](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#get-vocoder)'
  id: totrans-96
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[获取声码器](generated/torchaudio.prototype.pipelines.HiFiGANVocoderBundle.html#get-vocoder)'
- en: '[Pretrained Models](prototype.pipelines.html#id1)'
  id: totrans-97
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[预训练模型](prototype.pipelines.html#id1)'
- en: '[HIFIGAN_VOCODER_V3_LJSPEECH](generated/torchaudio.prototype.pipelines.HIFIGAN_VOCODER_V3_LJSPEECH.html)'
  id: totrans-98
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[HIFIGAN_VOCODER_V3_LJSPEECH](generated/torchaudio.prototype.pipelines.HIFIGAN_VOCODER_V3_LJSPEECH.html)'
- en: '[VGGish](prototype.pipelines.html#vggish)'
  id: totrans-99
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[VGGish](prototype.pipelines.html#vggish)'
- en: '[Interface](prototype.pipelines.html#id3)'
  id: totrans-100
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[接口](prototype.pipelines.html#id3)'
- en: '[VGGishBundle](generated/torchaudio.prototype.pipelines.VGGishBundle.html)'
  id: totrans-101
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[VGGishBundle](generated/torchaudio.prototype.pipelines.VGGishBundle.html)'
- en: '[Properties](generated/torchaudio.prototype.pipelines.VGGishBundle.html#properties)'
  id: totrans-102
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[属性](generated/torchaudio.prototype.pipelines.VGGishBundle.html#properties)'
- en: '[sample_rate](generated/torchaudio.prototype.pipelines.VGGishBundle.html#sample-rate)'
  id: totrans-103
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[采样率](generated/torchaudio.prototype.pipelines.VGGishBundle.html#sample-rate)'
- en: '[Methods](generated/torchaudio.prototype.pipelines.VGGishBundle.html#methods)'
  id: totrans-104
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[方法](generated/torchaudio.prototype.pipelines.VGGishBundle.html#methods)'
- en: '[get_input_processor](generated/torchaudio.prototype.pipelines.VGGishBundle.html#get-input-processor)'
  id: totrans-105
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[获取输入处理器](generated/torchaudio.prototype.pipelines.VGGishBundle.html#get-input-processor)'
- en: '[get_model](generated/torchaudio.prototype.pipelines.VGGishBundle.html#get-model)'
  id: totrans-106
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[get_model](generated/torchaudio.prototype.pipelines.VGGishBundle.html#get-model)'
- en: '[VGGishBundle.VGGish](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGish.html)'
  id: totrans-107
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[VGGishBundle.VGGish](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGish.html)'
- en: '[Methods](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGish.html#methods)'
  id: totrans-108
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[方法](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGish.html#methods)'
- en: '[forward](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGish.html#forward)'
  id: totrans-109
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[前向传播](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGish.html#forward)'
- en: '[VGGishBundle.VGGishInputProcessor](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGishInputProcessor.html)'
  id: totrans-110
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[VGGishBundle.VGGishInputProcessor](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGishInputProcessor.html)'
- en: '[Methods](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGishInputProcessor.html#methods)'
  id: totrans-111
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[方法](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGishInputProcessor.html#methods)'
- en: '[__call__](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGishInputProcessor.html#call)'
  id: totrans-112
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[__call__](generated/torchaudio.prototype.pipelines.VGGishBundle.VGGishInputProcessor.html#call)'
- en: '[Pretrained Models](prototype.pipelines.html#id6)'
  id: totrans-113
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[预训练模型](prototype.pipelines.html#id6)'
- en: '[VGGISH](generated/torchaudio.prototype.pipelines.VGGISH.html)'
  id: totrans-114
  prefs:
  - PREF_IND
  - PREF_IND
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[VGGISH](generated/torchaudio.prototype.pipelines.VGGISH.html)'
- en: '[torchaudio.prototype.transforms](prototype.transforms.html)'
  id: totrans-115
  prefs:
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[torchaudio.prototype.transforms](prototype.transforms.html)'
- en: '[BarkScale](generated/torchaudio.prototype.transforms.BarkScale.html)'
  id: totrans-116
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[BarkScale](generated/torchaudio.prototype.transforms.BarkScale.html)'
- en: '[BarkSpectrogram](generated/torchaudio.prototype.transforms.BarkSpectrogram.html)'
  id: totrans-117
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[BarkSpectrogram](generated/torchaudio.prototype.transforms.BarkSpectrogram.html)'
- en: '[ChromaScale](generated/torchaudio.prototype.transforms.ChromaScale.html)'
  id: totrans-118
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[ChromaScale](generated/torchaudio.prototype.transforms.ChromaScale.html)'
- en: '[ChromaSpectrogram](generated/torchaudio.prototype.transforms.ChromaSpectrogram.html)'
  id: totrans-119
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[ChromaSpectrogram](generated/torchaudio.prototype.transforms.ChromaSpectrogram.html)'
- en: '[InverseBarkScale](generated/torchaudio.prototype.transforms.InverseBarkScale.html)'
  id: totrans-120
  prefs:
  - PREF_IND
  - PREF_UL
  type: TYPE_NORMAL
  zh: '[InverseBarkScale](generated/torchaudio.prototype.transforms.InverseBarkScale.html)'