SpeechRecognition¶
- class flash.audio.speech_recognition.model.SpeechRecognition(backbone='facebook/wav2vec2-base-960h', processor_backbone=None, optimizer='Adam', lr_scheduler=None, learning_rate=None)[source]¶
The
SpeechRecognition
task is aTask
for converting speech to text. For more details, see Speech Recognition.- Parameters
backbone¶ (
str
) – Any speech recognition model from HuggingFace/transformers.learning_rate¶ (
Optional
[float
]) – Learning rate to use for training, defaults to1e-5
.optimizer¶ (
TypeVar
(OPTIMIZER_TYPE
,str
,Callable
,Tuple
[str
,Dict
[str
,Any
]],None
)) – Optimizer to use for training.lr_scheduler¶ (
Optional
[TypeVar
(LR_SCHEDULER_TYPE
,str
,Callable
,Tuple
[str
,Dict
[str
,Any
]],Tuple
[str
,Dict
[str
,Any
],Dict
[str
,Any
]],None
)]) – The LR scheduler to use during training.
- classmethod available_finetuning_strategies(cls)¶
Returns a list containing the keys of the available Finetuning Strategies.
- classmethod available_lr_schedulers(cls)¶
Returns a list containing the keys of the available LR schedulers.
- classmethod available_optimizers(cls)¶
Returns a list containing the keys of the available Optimizers.