Whisper

Whisper는 다양한 오디오 데이터셋으로 훈련된 다목적 음성 인식 모델입니다. 다국어 음성 인식, 음성 번역 및 언어 식별을 수행할 수 있습니다. 이 모델은 인코더-디코더 아키텍처를 사용하며 다양한 음향 환경에서 강력한 성능을 보여줍니다. RBLN NPU는 Optimum RBLN을 사용하여 Whisper 모델 추론을 가속화할 수 있습니다.

API 참조

Classes

RBLNWhisperForConditionalGeneration

Bases: RBLNModel, RBLNWhisperGenerationMixin

Whisper model for speech recognition and transcription optimized for RBLN NPU.

This model inherits from [RBLNModel]. It implements the methods to convert and run pre-trained transformers based Whisper model on RBLN devices by:

• transferring the checkpoint weights of the original into an optimized RBLN graph,
• compiling the resulting graph using the RBLN compiler.

Example (Short form):

import torch
from transformers import AutoProcessor
from datasets import load_dataset
from optimum.rbln import RBLNWhisperForConditionalGeneration

# Load processor and dataset
model_id = "openai/whisper-tiny"
processor = AutoProcessor.from_pretrained(model_id)
ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")

# Prepare input features
input_features = processor(
    ds[0]["audio"]["array"],
    sampling_rate=ds[0]["audio"]["sampling_rate"],
    return_tensors="pt"
).input_features

# Load and compile model (or load pre-compiled model)
model = RBLNWhisperForConditionalGeneration.from_pretrained(
    model_id=model_id,
    export=True,
    rbln_batch_size=1
)

# Generate transcription
outputs = model.generate(input_features=input_features, return_timestamps=True)
transcription = processor.batch_decode(outputs, skip_special_tokens=True)[0]
print(f"Transcription: {transcription}")

Functions

from_model(model, config=None, rbln_config=None, model_save_dir=None, subfolder='', **kwargs) classmethod

Converts and compiles a pre-trained HuggingFace library model into a RBLN model. This method performs the actual model conversion and compilation process.

Parameters:

Name	Type	Description	Default
model	PreTrainedModel	The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class.	required
config	Optional[PretrainedConfig]	The configuration object associated with the model.	None
rbln_config	Optional[Union[RBLNModelConfig, Dict]]	Configuration for RBLN model compilation and runtime. This can be provided as a dictionary or an instance of the model's configuration class (e.g., RBLNLlamaForCausalLMConfig for Llama models). For detailed configuration options, see the specific model's configuration class documentation.	None
kwargs	Any	Additional keyword arguments. Arguments with the prefix rbln_ are passed to rbln_config, while the remaining arguments are passed to the HuggingFace library.	{}

The method performs the following steps:

1. Compiles the PyTorch model into an optimized RBLN graph
2. Configures the model for the specified NPU device
3. Creates the necessary runtime objects if requested
4. Saves the compiled model and configurations

Returns:

Type	Description
RBLNModel	A RBLN model instance ready for inference on RBLN NPU devices.

generate(input_features=None, attention_mask=None, generation_config=None, return_segments=None, return_timestamps=None, return_token_timestamps=None, **kwargs)

The generate function is utilized in its standard form as in the HuggingFace transformers library. User can use this function to generate text from the model. Check the HuggingFace transformers documentation for more details.

Parameters:

Name	Type	Description	Default
input_features	Tensor	The input features to the model.	None
attention_mask	Tensor	Attention mask needs to be passed when doing long-form transcription using a batch size > 1.	None
generation_config	GenerationConfig	The generation configuration to be used as base parametrization for the generation call. **kwargs passed to generate matching the attributes of generation_config will override them. If generation_config is not provided, the default will be used, which had the following loading priority: 1) from the generation_config.json model file, if it exists; 2) from the model configuration. Please note that unspecified parameters will inherit GenerationConfig’s default values.	None
return_segments	bool	Whether to return segments.	None
return_timestamps	bool	Whether to return the timestamps with the text. For audios longer than 30 seconds, it is necessary to set return_timestamps=True.	None
return_token_timestamps	bool	Whether to return token timestamps.	None
kwargs	dict[str, Any]	Additional arguments passed to the generate function.	{}

Returns:

Type	Description
Union[ModelOutput, Dict[str, Any], LongTensor]	Transcribes or translates log-mel input features to a sequence of auto-regressively generated token ids.

from_pretrained(model_id, export=None, rbln_config=None, **kwargs) classmethod

The from_pretrained() function is utilized in its standard form as in the HuggingFace transformers library. User can use this function to load a pre-trained model from the HuggingFace library and convert it to a RBLN model to be run on RBLN NPUs.

Parameters:

Name	Type	Description	Default
model_id	Union[str, Path]	The model id of the pre-trained model to be loaded. It can be downloaded from the HuggingFace model hub or a local path, or a model id of a compiled model using the RBLN Compiler.	required
export	Optional[bool]	A boolean flag to indicate whether the model should be compiled. If None, it will be determined based on the existence of the compiled model files in the model_id.	None
rbln_config	Optional[Union[Dict, RBLNModelConfig]]	Configuration for RBLN model compilation and runtime. This can be provided as a dictionary or an instance of the model's configuration class (e.g., RBLNLlamaForCausalLMConfig for Llama models). For detailed configuration options, see the specific model's configuration class documentation.	None
kwargs	Any	Additional keyword arguments. Arguments with the prefix rbln_ are passed to rbln_config, while the remaining arguments are passed to the HuggingFace library.	{}

Returns:

Type	Description
RBLNModel	A RBLN model instance ready for inference on RBLN NPU devices.

save_pretrained(save_directory, push_to_hub=False, **kwargs)

Saves a model and its configuration file to a directory, so that it can be re-loaded using the [~optimum.rbln.modeling_base.RBLNBaseModel.from_pretrained] class method.

Parameters:

Name	Type	Description	Default
save_directory	Union[str, Path]	Directory where to save the model file.	required
push_to_hub	bool	Whether or not to push your model to the HuggingFace model hub after saving it.	False

Classes

RBLNWhisperForConditionalGenerationConfig

Bases: RBLNModelConfig

Configuration class for RBLNWhisperForConditionalGeneration.

This configuration class stores the configuration parameters specific to RBLN-optimized Whisper models for speech recognition and transcription tasks.

Functions

__init__(batch_size=None, token_timestamps=None, use_attention_mask=None, enc_max_seq_len=None, dec_max_seq_len=None, kvcache_num_blocks=None, kvcache_block_size=None, **kwargs)

Parameters:

Name	Type	Description	Default
batch_size	int	The batch size for inference. Defaults to 1.	None
token_timestamps	bool	Whether to output token timestamps during generation. Defaults to False.	None
use_attention_mask	bool	Whether to use attention masks during inference. This is automatically	None
enc_max_seq_len	int	Maximum sequence length for the encoder.	None
dec_max_seq_len	int	Maximum sequence length for the decoder.	None
kvcache_num_blocks	int	The total number of blocks to allocate for the PagedAttention KV cache for the SelfAttention. Defaults to batch_size.	None
kvcache_block_size	int	Sets the size (in number of tokens) of each block in the PagedAttention KV cache for the SelfAttention. Defaults to dec_max_seq_len.	None
kwargs	Any	Additional arguments passed to the parent RBLNModelConfig.	{}

Raises:

Type	Description
ValueError	If batch_size is not a positive integer.

load(path, **kwargs) classmethod

Load a RBLNModelConfig from a path.

Parameters:

Name	Type	Description	Default
path	str	Path to the RBLNModelConfig file or directory containing the config file.	required
kwargs	Any	Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.	{}

Returns:

Name	Type	Description
RBLNModelConfig	RBLNModelConfig	The loaded configuration instance.

Note

This method loads the configuration from the specified path and applies any provided overrides. If the loaded configuration class doesn't match the expected class, a warning will be logged.