|
otherwise, the LM won't be available to the pool's sub-processes |
|
select number of processes and batch_size based on number of CPU cores available and on dataset size |
|
with get_context("fork").Pool(processes=2) as pool: |
|
result = dataset.map( |
|
map_to_pred, batched=True, batch_size=2, fn_kwargs={"pool": pool}, remove_columns=["speech"] |
|
) |
|
result["transcription"][:2] |
|
['MISTER QUILTER IS THE APOSTLE OF THE MIDDLE CLASSES AND WE ARE GLAD TO WELCOME HIS GOSPEL', "NOR IS MISTER COULTER'S MANNER LESS INTERESTING THAN HIS MATTER"] |
|
|
|
Wav2Vec2 specific outputs |
|
[[autodoc]] models.wav2vec2_with_lm.processing_wav2vec2_with_lm.Wav2Vec2DecoderWithLMOutput |
|
[[autodoc]] models.wav2vec2.modeling_wav2vec2.Wav2Vec2BaseModelOutput |
|
[[autodoc]] models.wav2vec2.modeling_wav2vec2.Wav2Vec2ForPreTrainingOutput |
|
[[autodoc]] models.wav2vec2.modeling_flax_wav2vec2.FlaxWav2Vec2BaseModelOutput |
|
[[autodoc]] models.wav2vec2.modeling_flax_wav2vec2.FlaxWav2Vec2ForPreTrainingOutput |
|
|
|
Wav2Vec2Model |
|
[[autodoc]] Wav2Vec2Model |
|
- forward |
|
Wav2Vec2ForCTC |
|
[[autodoc]] Wav2Vec2ForCTC |
|
- forward |
|
- load_adapter |
|
Wav2Vec2ForSequenceClassification |
|
[[autodoc]] Wav2Vec2ForSequenceClassification |
|
- forward |
|
Wav2Vec2ForAudioFrameClassification |
|
[[autodoc]] Wav2Vec2ForAudioFrameClassification |
|
- forward |
|
Wav2Vec2ForXVector |
|
[[autodoc]] Wav2Vec2ForXVector |
|
- forward |
|
Wav2Vec2ForPreTraining |
|
[[autodoc]] Wav2Vec2ForPreTraining |
|
- forward |
|
|
|
TFWav2Vec2Model |
|
[[autodoc]] TFWav2Vec2Model |
|
- call |
|
TFWav2Vec2ForSequenceClassification |
|
[[autodoc]] TFWav2Vec2ForSequenceClassification |
|
- call |
|
TFWav2Vec2ForCTC |
|
[[autodoc]] TFWav2Vec2ForCTC |
|
- call |
|
|
|
FlaxWav2Vec2Model |
|
[[autodoc]] FlaxWav2Vec2Model |
|
- call |
|
FlaxWav2Vec2ForCTC |
|
[[autodoc]] FlaxWav2Vec2ForCTC |
|
- call |
|
FlaxWav2Vec2ForPreTraining |
|
[[autodoc]] FlaxWav2Vec2ForPreTraining |
|
- call |