# Whisper [[whisper]]

## 개요 [[overview]]

Whisper 모델은 Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, Ilya Sutskever에 의해 [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf)에서 제안되었습니다.

논문의 초록은 다음과 같습니다:

*우리는 인터넷에서 대량의 오디오를 글로 옮긴 것을 예측하도록 간단히 훈련된 음성 처리 시스템의 성능을 연구합니다. 68만 시간의 다국어 및 다중 작업 지도(multitask supervision)에 확장했을 때, 결과 모델은 표준 벤치마크에 잘 일반화되며, 미세 조정이 필요 없는 제로샷 전송 설정에서 이전의 완전히 지도된(fully-supervised) 결과와 경쟁할 수 있는 경우가 많습니다. 사람과 비교하면, 이 모델은 사람의 정확도와 견고성에 근접합니다. 우리는 강력한 음성 처리를 위한 추가 작업의 기반이 될 모델과 추론 코드를 공개합니다.*

팁:

- 이 모델은 일반적으로 별도의 미세 조정 없이도 잘 작동합니다.
- 아키텍처는 고전적인 인코더-디코더 아키텍처를 따르기 때문에, 추론을 위해 [generate()](/docs/transformers/v5.4.0/ko/main_classes/text_generation#transformers.GenerationMixin.generate) 함수를 사용합니다.
- 현재 추론은 짧은 형식에만 구현되어 있으며, 오디오는 30초 미만의 세그먼트로 미리 분할되어야 합니다. 타임스탬프를 포함한 긴 형식에 대한 추론은 향후 릴리스에서 구현될 예정입니다.
- [WhisperProcessor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperProcessor)를 사용하여 모델에 사용할 오디오를 준비하고, 예측된 ID를 텍스트로 디코딩할 수 있습니다.

- 모델과 프로세서를 변환하려면 다음을 사용하는 것이 좋습니다:

```bash
python src/transformers/models/whisper/convert_openai_to_hf.py --checkpoint_path "" --pytorch_dump_folder_path "Arthur/whisper-3" --convert_preprocessor True
```
스크립트는 OpenAI 체크포인트에서 필요한 모든 매개변수를 자동으로 결정합니다. OpenAI 변환을 수행하려면 `tiktoken` 라이브러리를 설치해야 합니다.
라이브러리를 설치해야 OpenAI 토큰화기를 `tokenizers` 버전으로 변환할 수 있습니다.

이 모델은 [Arthur Zucker](https://huggingface.co/ArthurZ)에 의해 제공되었습니다. 이 모델의 Tensorflow 버전은 [amyeroberts](https://huggingface.co/amyeroberts)에 의해 제공되었습니다.
원본 코드는 [여기](https://github.com/openai/whisper)에서 찾을 수 있습니다.

## WhisperConfig [[whisperconfig]][[transformers.WhisperConfig]]

#### transformers.WhisperConfig[[transformers.WhisperConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/configuration_whisper.py#L50)

This is the configuration class to store the configuration of a WhisperModel. It is used to instantiate a Whisper
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
defaults will yield a similar configuration to that of the [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.4.0/ko/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.4.0/ko/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:

```python
>>> from transformers import WhisperConfig, WhisperModel

>>> # Initializing a Whisper tiny style configuration
>>> configuration = WhisperConfig()

>>> # Initializing a model (with random weights) from the tiny style configuration
>>> model = WhisperModel(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config
```

**Parameters:**

is_encoder_decoder (`bool`, *optional*, defaults to `True`) : Whether the model is used as an encoder/decoder or not.

vocab_size (`int`, *optional*, defaults to `51865`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`.

num_mel_bins (`int`, *optional*, defaults to `80`) : Number of mel features used per input frame. Should correspond to the value used in the `AutoFeatureExtractor` class.

encoder_layers (`int`, *optional*, defaults to `4`) : Number of hidden layers in the Transformer encoder. Will use the same value as `num_layers` if not set.

encoder_attention_heads (`int`, *optional*, defaults to `6`) : Number of attention heads for each attention layer in the Transformer encoder.

decoder_layers (`int`, *optional*, defaults to `4`) : Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set.

decoder_attention_heads (`int`, *optional*, defaults to `6`) : Number of attention heads for each attention layer in the Transformer decoder.

decoder_ffn_dim (`int`, *optional*, defaults to `1536`) : Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.

encoder_ffn_dim (`int`, *optional*, defaults to `1536`) : Dimensionality of the "intermediate" (often named feed-forward) layer in encoder.

encoder_layerdrop (`Union[float, int]`, *optional*, defaults to `0.0`) : The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details.

decoder_layerdrop (`Union[float, int]`, *optional*, defaults to `0.0`) : The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details.

decoder_start_token_id (`int`, *optional*, defaults to `50257`) : If an encoder-decoder model starts decoding with a different token than `bos`, the id of that token.

use_cache (`bool`, *optional*, defaults to `True`) : Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True` or when the model is a decoder-only generative model.

activation_function (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc.

d_model (`int`, *optional*, defaults to `384`) : Size of the encoder layers and the pooler layer.

dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The ratio for all dropout layers.

attention_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities.

activation_dropout (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for activations inside the fully connected layer.

init_std (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

scale_embedding (`bool`, *optional*, defaults to `False`) : Whether to scale embeddings by dividing by sqrt(d_model).

max_source_positions (`int`, *optional*, defaults to 1500) : The maximum sequence length of log-mel filter-bank features that this model might ever be used with.

max_target_positions (`int`, *optional*, defaults to 448) : The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).

pad_token_id (`int`, *optional*, defaults to `50256`) : Token id used for padding in the vocabulary.

bos_token_id (`int`, *optional*, defaults to `50256`) : Token id used for beginning-of-stream in the vocabulary.

eos_token_id (`Union[int, list[int]]`, *optional*, defaults to `50256`) : Token id used for end-of-stream in the vocabulary.

suppress_tokens (`list[int]`, *optional*) : A list containing the non-speech tokens that will be used by the logit processor in the `generate` function. NON_SPEECH_TOKENS and NON_SPEECH_TOKENS_MULTI each correspond to the `english-only` and the `multilingual` model.

begin_suppress_tokens (`list[int]`, *optional*, defaults to `[220,50256]`) : A list containing tokens that will be suppressed at the beginning of the sampling process. Initialized as the token for `" "` (`blank_token_id`) and the `eos_token_id`

use_weighted_layer_sum (`bool`, *optional*, defaults to `False`) : Whether to use a weighted average of layer outputs with learned weights. Only relevant when using an instance of [WhisperForAudioClassification](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperForAudioClassification).

classifier_proj_size (`int`, *optional*, defaults to 256) : Dimensionality of the projection before token mean-pooling for classification. Only relevant when using an instance of [WhisperForAudioClassification](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperForAudioClassification).

apply_spec_augment (`bool`, *optional*, defaults to `False`) : Whether to apply *SpecAugment* data augmentation to the outputs of the feature encoder. For reference see [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://huggingface.co/papers/1904.08779).

mask_time_prob (`float`, *optional*, defaults to 0.05) : Percentage (between 0 and 1) of all feature vectors along the time axis which will be masked. The masking procedure generates `mask_time_prob*len(time_axis)/mask_time_length` independent masks over the axis. If reasoning from the probability of each feature vector to be chosen as the start of the vector span to be masked, *mask_time_prob* should be `prob_vector_start*mask_time_length`. Note that overlap may decrease the actual percentage of masked vectors. This is only relevant if `apply_spec_augment == True`.

mask_time_length (`int`, *optional*, defaults to 10) : Length of vector span along the time axis.

mask_time_min_masks (`int`, *optional*, defaults to 2), : The minimum number of masks of length `mask_feature_length` generated along the time axis, each time step, irrespectively of `mask_feature_prob`. Only relevant if ''mask_time_prob*len(time_axis)/mask_time_length >> # instantiate the tokenizer and set the prefix token to Spanish
>>> tokenizer = WhisperTokenizerFast.from_pretrained("openai/whisper-tiny", language="spanish")
>>> # now switch the prefix token from Spanish to French
>>> tokenizer.set_prefix_tokens(language="french")
```

**Parameters:**

vocab_file (`str`, *optional*) : Path to the vocabulary file.

merges_file (`str`, *optional*) : Path to the merges file.

normalizer_file (`str`, *optional*) : Path to the normalizer_file file.

tokenizer_file (`str`, *optional*) : Path to [tokenizers](https://github.com/huggingface/tokenizers) file (generally has a .json extension) that contains everything needed to load the tokenizer.

unk_token (`str`, *optional*, defaults to `""`) : The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.

bos_token (`str`, *optional*, defaults to `""`) : The beginning of sequence token. The `decoder_start_token_id` is used to set the first token as `""` when generating.

eos_token (`str`, *optional*, defaults to `""`) : The end of sequence token.

add_prefix_space (`bool`, *optional*, defaults to `False`) : Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (Whisper tokenizer detect beginning of words by the preceding space).

language (`str`, *optional*) : The language of the transcription text. The corresponding language id token is appended to the start of the sequence for multilingual speech recognition and speech translation tasks, e.g. for Spanish the token `""` is appended to the start of sequence. This should be used for multilingual fine-tuning only.

task (`str`, *optional*) : Task identifier to append at the start of sequence (if any). This should be used for mulitlingual fine-tuning, with `"transcribe"` for speech recognition and `"translate"` for speech translation.

predict_timestamps (`bool`, *optional*, defaults to `False`) : Whether to omit the `` token at the start of the sequence.
#### get_special_tokens_mask[[transformers.WhisperTokenizer.get_special_tokens_mask]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/tokenization_whisper.py#L659)

Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer `prepare_for_model` method.

**Parameters:**

token_ids_0 (`list[int]`) : List of IDs.

token_ids_1 (`list[int]`, *optional*) : Optional second list of IDs for sequence pairs.

already_has_special_tokens (`bool`, *optional*, defaults to `False`) : Whether or not the token list is already formatted with special tokens for the model.

**Returns:**

``list[int]``

A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
#### save_vocabulary[[transformers.WhisperTokenizer.save_vocabulary]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/tokenization_whisper.py#L545)

## WhisperTokenizerFast [[whispertokenizerfast]][[transformers.WhisperTokenizer]]

#### transformers.WhisperTokenizer[[transformers.WhisperTokenizer]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/tokenization_whisper.py#L163)

Construct a "fast" Whisper tokenizer (backed by HuggingFace's *tokenizers* library).

This tokenizer inherits from [PreTrainedTokenizerFast](/docs/transformers/v5.4.0/ko/main_classes/tokenizer#transformers.TokenizersBackend) which contains most of the main methods. Users should
refer to this superclass for more information regarding those methods.

set_prefix_tokenstransformers.WhisperTokenizer.set_prefix_tokenshttps://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/tokenization_whisper.py#L575[{"name": "language", "val": ": str | None = None"}, {"name": "task", "val": ": str | None = None"}, {"name": "predict_timestamps", "val": ": bool | None = None"}]- **language** (`str`, *optional*, defaults to `None`) --
  The language of the transcription text.
- **task** (`str`, *optional*, defaults to `None`) --
  Task identifier to append at the start of sequence (if any).
- **predict_timestamps** (`bool`, *optional*, defaults to `None`) --
  Whether to omit the `` token at the start of the sequence.0

Override the prefix tokens appended to the start of the label sequence. This method can be used standalone to

update the prefix tokens as required when fine-tuning. Example:

```python
>>> # instantiate the tokenizer and set the prefix token to Spanish
>>> tokenizer = WhisperTokenizerFast.from_pretrained("openai/whisper-tiny", language="spanish")
>>> # now switch the prefix token from Spanish to French
>>> tokenizer.set_prefix_tokens(language="french")
```

**Parameters:**

vocab_file (`str`, *optional*) : Path to the vocabulary file.

merges_file (`str`, *optional*) : Path to the merges file.

normalizer_file (`str`, *optional*) : Path to the normalizer_file file.

tokenizer_file (`str`, *optional*) : Path to [tokenizers](https://github.com/huggingface/tokenizers) file (generally has a .json extension) that contains everything needed to load the tokenizer.

unk_token (`str`, *optional*, defaults to `""`) : The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.

bos_token (`str`, *optional*, defaults to `""`) : The beginning of sequence token. The `decoder_start_token_id` is used to set the first token as `""` when generating.

eos_token (`str`, *optional*, defaults to `""`) : The end of sequence token.

add_prefix_space (`bool`, *optional*, defaults to `False`) : Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (Whisper tokenizer detect beginning of words by the preceding space).

language (`str`, *optional*) : The language of the transcription text. The corresponding language id token is appended to the start of the sequence for multilingual speech recognition and speech translation tasks, e.g. for Spanish the token `""` is appended to the start of sequence. This should be used for multilingual fine-tuning only.

task (`str`, *optional*) : Task identifier to append at the start of sequence (if any). This should be used for mulitlingual fine-tuning, with `"transcribe"` for speech recognition and `"translate"` for speech translation.

predict_timestamps (`bool`, *optional*, defaults to `False`) : Whether to omit the `` token at the start of the sequence.
#### get_special_tokens_mask[[transformers.WhisperTokenizer.get_special_tokens_mask]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/tokenization_whisper.py#L659)

Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
special tokens using the tokenizer `prepare_for_model` method.

**Parameters:**

token_ids_0 (`list[int]`) : List of IDs.

token_ids_1 (`list[int]`, *optional*) : Optional second list of IDs for sequence pairs.

already_has_special_tokens (`bool`, *optional*, defaults to `False`) : Whether or not the token list is already formatted with special tokens for the model.

**Returns:**

``list[int]``

A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
#### save_vocabulary[[transformers.WhisperTokenizer.save_vocabulary]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/tokenization_whisper.py#L545)

## WhisperFeatureExtractor [[whisperfeatureextractor]][[transformers.WhisperFeatureExtractor]]

#### transformers.WhisperFeatureExtractor[[transformers.WhisperFeatureExtractor]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/feature_extraction_whisper.py#L33)

Constructs a Whisper feature extractor.

This feature extractor inherits from [SequenceFeatureExtractor](/docs/transformers/v5.4.0/ko/main_classes/feature_extractor#transformers.SequenceFeatureExtractor) which contains
most of the main methods. Users should refer to this superclass for more information regarding those methods.

This class extracts mel-filter bank features from raw speech using a custom numpy implementation of the `Short Time
Fourier Transform` which should match pytorch's `torch.stft` equivalent.

__call__transformers.WhisperFeatureExtractor.__call__https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/feature_extraction_whisper.py#L189[{"name": "raw_speech", "val": ": numpy.ndarray | list[float] | list[numpy.ndarray] | list[list[float]]"}, {"name": "truncation", "val": ": bool = True"}, {"name": "pad_to_multiple_of", "val": ": int | None = None"}, {"name": "return_tensors", "val": ": str | transformers.utils.generic.TensorType | None = None"}, {"name": "return_attention_mask", "val": ": bool | None = None"}, {"name": "padding", "val": ": str | None = 'max_length'"}, {"name": "max_length", "val": ": int | None = None"}, {"name": "sampling_rate", "val": ": int | None = None"}, {"name": "do_normalize", "val": ": bool | None = None"}, {"name": "device", "val": ": str | None = 'cpu'"}, {"name": "**kwargs", "val": ""}]- **raw_speech** (`np.ndarray`, `list[float]`, `list[np.ndarray]`, `list[list[float]]`) --
  The sequence or batch of sequences to be padded. Each sequence can be a numpy array, a list of float
  values, a list of numpy arrays or a list of list of float values. Must be mono channel audio, not
  stereo, i.e. single float per timestep.
- **truncation** (`bool`, *optional*, default to `True`) --
  Activates truncation to cut input sequences longer than *max_length* to *max_length*.
- **pad_to_multiple_of** (`int`, *optional*, defaults to None) --
  If set will pad the sequence to a multiple of the provided value.

  This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability
  `>= 7.5` (Volta), or on TPUs which benefit from having sequence lengths be a multiple of 128.
- **return_tensors** (`str` or [TensorType](/docs/transformers/v5.4.0/ko/internal/file_utils#transformers.TensorType), *optional*) --
  If set, will return tensors instead of list of python integers. Acceptable values are:

  - `'pt'`: Return PyTorch `torch.Tensor` objects.
  - `'np'`: Return Numpy `np.ndarray` objects.
- **return_attention_mask** (`bool`, *optional*) --
  Whether to return the attention mask. If left to the default, will return the attention mask according
  to the specific feature_extractor's default.

  [What are attention masks?](../glossary#attention-mask)

  

  For Whisper models, `attention_mask` should always be passed for batched inference, to avoid subtle
  bugs.

  
- **padding** (`str` or [PaddingStrategy](/docs/transformers/v5.4.0/ko/internal/file_utils#transformers.utils.PaddingStrategy), *optional*, defaults to `'max_length'`) --
  Activates and controls padding. Accepts the following values:

  - `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence is
    provided).
  - `'max_length'` (default): Pad to a maximum length specified with the argument `max_length` or to the
    maximum acceptable input length for the model if that argument is not provided.
  - `'do_not_pad'`: No padding (i.e., can output a batch with sequences of different lengths).
- **max_length** (`int`, *optional*) --
  Controls the maximum length to use by one of the truncation/padding parameters.

  If left unset or set to `None`, this will use the predefined model maximum length if a maximum length
  is required by one of the truncation/padding parameters. If the model has no specific maximum input
  length (like XLNet) truncation/padding to a maximum length will be deactivated.
- **sampling_rate** (`int`, *optional*) --
  The sampling rate at which the `raw_speech` input was sampled. It is strongly recommended to pass
  `sampling_rate` at the forward call to prevent silent errors and allow automatic speech recognition
  pipeline.
- **do_normalize** (`bool`, *optional*, defaults to `False`) --
  Whether or not to zero-mean unit-variance normalize the input. Normalizing can help to significantly
  improve the performance of the model.
- **device** (`str`, *optional*, defaults to `'cpu'`) --
  Specifies the device for computation of the log-mel spectrogram of audio signals in the
  `_torch_extract_fbank_features` method. (e.g., "cpu", "cuda")
- ****kwargs** -- Not supported by WhisperFeatureExtractor.__call__() and ignored.0
Main method to featurize and prepare for the model one or several sequence(s). Implementation uses PyTorch
for the STFT computation if available, otherwise a slower NumPy based one.

**Parameters:**

feature_size (`int`, *optional*, defaults to 80) : The feature dimension of the extracted features.

sampling_rate (`int`, *optional*, defaults to 16000) : The sampling rate at which the audio files should be digitalized expressed in hertz (Hz).

hop_length (`int`, *optional*, defaults to 160) : Length of the overlapping windows for the STFT used to obtain the Mel Frequency coefficients.

chunk_length (`int`, *optional*, defaults to 30) : The maximum number of chunks of `sampling_rate` samples used to trim and pad longer or shorter audio sequences.

n_fft (`int`, *optional*, defaults to 400) : Size of the Fourier transform.

padding_value (`float`, *optional*, defaults to 0.0) : Padding value used to pad the audio. Should correspond to silences.

dither (`float`, *optional*, defaults to 0.0) : Adds dithering. In other words, adds a small Gaussian noise to each frame. E.g. use 0.0001 to add dithering with a normal distribution centered around 0.0 with standard deviation 0.0001 (assuming [-1,+1] range of raw_speech). The value 0.0 means no dithering. Dithering has similar effect as `spectrogram(mel_floor=...)`. It reduces the high log_mel_fbank values for signals with hard-zero sections, when VAD cutoff is present in the signal.

## WhisperProcessor [[whisperprocessor]][[transformers.WhisperProcessor]]

#### transformers.WhisperProcessor[[transformers.WhisperProcessor]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/processing_whisper.py#L23)

Constructs a WhisperProcessor which wraps a feature extractor and a tokenizer into a single processor.

[WhisperProcessor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperProcessor) offers all the functionalities of [WhisperFeatureExtractor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor) and [WhisperTokenizer](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperTokenizer). See the
[~WhisperFeatureExtractor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor) and [~WhisperTokenizer](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperTokenizer) for more information.

__call__transformers.WhisperProcessor.__call__https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/processing_whisper.py#L30[{"name": "*args", "val": ""}, {"name": "**kwargs", "val": ""}]- **return_tensors** (`str` or [TensorType](/docs/transformers/v5.4.0/ko/internal/file_utils#transformers.TensorType), *optional*) --
  If set, will return tensors of a particular framework. Acceptable values are:

  - `'pt'`: Return PyTorch `torch.Tensor` objects.
  - `'np'`: Return NumPy `np.ndarray` objects.0

**Parameters:**

feature_extractor (`WhisperFeatureExtractor`) : The feature extractor is a required input.

tokenizer (`WhisperTokenizer`) : The tokenizer is a required input.
#### from_pretrained[[transformers.WhisperProcessor.from_pretrained]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/processing_utils.py#L1372)

Instantiate a processor associated with a pretrained model.

This class method is simply calling the feature extractor
[from_pretrained()](/docs/transformers/v5.4.0/ko/main_classes/feature_extractor#transformers.FeatureExtractionMixin.from_pretrained), image processor
[ImageProcessingMixin](/docs/transformers/v5.4.0/ko/internal/image_processing_utils#transformers.ImageProcessingMixin) and the tokenizer
`~tokenization_utils_base.PreTrainedTokenizer.from_pretrained` methods. Please refer to the docstrings of the
methods above for more information.

**Parameters:**

pretrained_model_name_or_path (`str` or `os.PathLike`) : This can be either:  - a string, the *model id* of a pretrained feature_extractor hosted inside a model repo on huggingface.co. - a path to a *directory* containing a feature extractor file saved using the [save_pretrained()](/docs/transformers/v5.4.0/ko/main_classes/feature_extractor#transformers.FeatureExtractionMixin.save_pretrained) method, e.g., `./my_model_directory/`. - a path to a saved feature extractor JSON *file*, e.g., `./my_model_directory/preprocessor_config.json`.

- ****kwargs** : Additional keyword arguments passed along to both [from_pretrained()](/docs/transformers/v5.4.0/ko/main_classes/feature_extractor#transformers.FeatureExtractionMixin.from_pretrained) and `~tokenization_utils_base.PreTrainedTokenizer.from_pretrained`.
#### save_pretrained[[transformers.WhisperProcessor.save_pretrained]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/processing_utils.py#L799)

Saves the attributes of this processor (feature extractor, tokenizer...) in the specified directory so that it
can be reloaded using the [from_pretrained()](/docs/transformers/v5.4.0/ko/main_classes/processors#transformers.ProcessorMixin.from_pretrained) method.

This class method is simply calling [save_pretrained()](/docs/transformers/v5.4.0/ko/main_classes/feature_extractor#transformers.FeatureExtractionMixin.save_pretrained) and
[save_pretrained()](/docs/transformers/v5.4.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.save_pretrained). Please refer to the docstrings of the
methods above for more information.

**Parameters:**

save_directory (`str` or `os.PathLike`) : Directory where the feature extractor JSON file and the tokenizer files will be saved (directory will be created if it does not exist).

push_to_hub (`bool`, *optional*, defaults to `False`) : Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with `repo_id` (will default to the name of `save_directory` in your namespace).

kwargs (`dict[str, Any]`, *optional*) : Additional key word arguments passed along to the [push_to_hub()](/docs/transformers/v5.4.0/ko/main_classes/model#transformers.utils.PushToHubMixin.push_to_hub) method.
#### batch_decode[[transformers.WhisperProcessor.batch_decode]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/processing_utils.py#L1609)

This method forwards all its arguments to PreTrainedTokenizer's [batch_decode()](/docs/transformers/v5.4.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.batch_decode). Please
refer to the docstring of this method for more information.
#### decode[[transformers.WhisperProcessor.decode]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/processing_utils.py#L1618)

This method forwards all its arguments to PreTrainedTokenizer's [decode()](/docs/transformers/v5.4.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.decode). Please refer to
the docstring of this method for more information.

## WhisperModel [[whispermodel]][[transformers.WhisperModel]]

#### transformers.WhisperModel[[transformers.WhisperModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/modeling_whisper.py#L800)

The bare Whisper Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/v5.4.0/ko/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
and behavior.

forwardtransformers.WhisperModel.forwardhttps://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/modeling_whisper.py#L865[{"name": "input_features", "val": ": torch.FloatTensor | None = None"}, {"name": "attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": tuple[tuple[torch.FloatTensor]] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "decoder_inputs_embeds", "val": ": tuple[torch.FloatTensor] | None = None"}, {"name": "decoder_position_ids", "val": ": tuple[torch.LongTensor] | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_features** (`torch.FloatTensor` of shape `(batch_size, sequence_length, feature_dim)`, *optional*) --
  The tensors corresponding to the input audio features. Audio features can be obtained using
  [WhisperFeatureExtractor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor). See [WhisperFeatureExtractor.__call__()](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor.__call__) for details ([WhisperProcessor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperProcessor) uses
  [WhisperFeatureExtractor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor) for processing audios).
- **attention_mask** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.

  [What are attention masks?](../glossary#attention-mask)
- **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [WhisperTokenizer](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.4.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.4.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are decoder input IDs?](../glossary#decoder-input-ids)

  Whisper uses the `decoder_start_token_id` as the starting token for `decoder_input_ids` generation. If
  `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see
  `past_key_values`).
- **decoder_attention_mask** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also
  be used by default.

  If you want to change padding behavior, you should read
  `modeling_whisper._prepare_decoder_attention_mask` and modify to your needs. See diagram 1 in [the BART
  paper](https://huggingface.co/papers/1910.13461) for more information on the default strategy.
- **encoder_outputs** (`tuple[tuple[torch.FloatTensor]]`, *optional*) --
  Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`)
  `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of
  hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
- **past_key_values** (`~cache_utils.Cache`, *optional*) --
  Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values`
  returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.

  Only [Cache](/docs/transformers/v5.4.0/ko/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.4.0/ko/internal/generation_utils#transformers.DynamicCache) will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **decoder_inputs_embeds** (`tuple[torch.FloatTensor]` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded
  representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be
  input (see `past_key_values`). This is useful if you want more control over how to convert
  `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix.

  If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value
  of `inputs_embeds`.
- **decoder_position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
  config.n_positions - 1]`.

  [What are position IDs?](../glossary#position-ids)
- **use_cache** (`bool`, *optional*) --
  If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
  `past_key_values`).0[Seq2SeqModelOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqModelOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([WhisperConfig](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperConfig)) and inputs.
The [WhisperModel](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module`
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.

- **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) -- Sequence of hidden-states at the output of the last layer of the decoder of the model.

  If `past_key_values` is used only the last hidden-state of the sequences of shape `(batch_size, 1,
  hidden_size)` is output.
- **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [EncoderDecoderCache](/docs/transformers/v5.4.0/ko/internal/generation_utils#transformers.EncoderDecoderCache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
- **decoder_hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the optional initial embedding outputs.
- **decoder_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.
- **cross_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
  weighted average in the cross-attention heads.
- **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model.
- **encoder_hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the optional initial embedding outputs.
- **encoder_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.

Example:
```python
>>> import torch
>>> from transformers import AutoFeatureExtractor, WhisperModel
>>> from datasets import load_dataset

>>> model = WhisperModel.from_pretrained("openai/whisper-base")
>>> feature_extractor = AutoFeatureExtractor.from_pretrained("openai/whisper-base")
>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
>>> inputs = feature_extractor(ds[0]["audio"]["array"], return_tensors="pt")
>>> input_features = inputs.input_features
>>> decoder_input_ids = torch.tensor([[1, 1]]) * model.config.decoder_start_token_id
>>> last_hidden_state = model(input_features, decoder_input_ids=decoder_input_ids).last_hidden_state
>>> list(last_hidden_state.shape)
[1, 2, 512]
```

**Parameters:**

config ([WhisperConfig](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.4.0/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[Seq2SeqModelOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or `tuple(torch.FloatTensor)``

A [Seq2SeqModelOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.Seq2SeqModelOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([WhisperConfig](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperConfig)) and inputs.
#### _mask_input_features[[transformers.WhisperModel._mask_input_features]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/modeling_whisper.py#L822)

Masks extracted features along time axis and/or along feature axis according to
[SpecAugment](https://huggingface.co/papers/1904.08779).

## WhisperForConditionalGeneration [[whisperforconditionalgeneration]][[transformers.WhisperForConditionalGeneration]]

#### transformers.WhisperForConditionalGeneration[[transformers.WhisperForConditionalGeneration]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/modeling_whisper.py#L964)

The Whisper Model with a language modeling head. Can be used for automatic speech recognition.

This model inherits from [PreTrainedModel](/docs/transformers/v5.4.0/ko/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
and behavior.

forwardtransformers.WhisperForConditionalGeneration.forwardhttps://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/modeling_whisper.py#L993[{"name": "input_features", "val": ": torch.FloatTensor | None = None"}, {"name": "attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "decoder_attention_mask", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": tuple[tuple[torch.FloatTensor]] | None = None"}, {"name": "past_key_values", "val": ": transformers.cache_utils.Cache | None = None"}, {"name": "decoder_inputs_embeds", "val": ": tuple[torch.FloatTensor] | None = None"}, {"name": "decoder_position_ids", "val": ": tuple[torch.LongTensor] | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "use_cache", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **input_features** (`torch.FloatTensor` of shape `(batch_size, sequence_length, feature_dim)`, *optional*) --
  The tensors corresponding to the input audio features. Audio features can be obtained using
  [WhisperFeatureExtractor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor). See [WhisperFeatureExtractor.__call__()](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor.__call__) for details ([WhisperProcessor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperProcessor) uses
  [WhisperFeatureExtractor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor) for processing audios).
- **attention_mask** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Mask to avoid performing attention on padding token indices. Mask values selected in `[0, 1]`:

  - 1 for tokens that are **not masked**,
  - 0 for tokens that are **masked**.

  [What are attention masks?](../glossary#attention-mask)
- **decoder_input_ids** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Indices of decoder input sequence tokens in the vocabulary.

  Indices can be obtained using [WhisperTokenizer](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.4.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/v5.4.0/ko/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details.

  [What are decoder input IDs?](../glossary#decoder-input-ids)

  Whisper uses the `decoder_start_token_id` as the starting token for `decoder_input_ids` generation. If
  `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see
  `past_key_values`).
- **decoder_attention_mask** (`torch.LongTensor` of shape `(batch_size, target_sequence_length)`, *optional*) --
  Default behavior: generate a tensor that ignores pad tokens in `decoder_input_ids`. Causal mask will also
  be used by default.

  If you want to change padding behavior, you should read
  `modeling_whisper._prepare_decoder_attention_mask` and modify to your needs. See diagram 1 in [the BART
  paper](https://huggingface.co/papers/1910.13461) for more information on the default strategy.
- **encoder_outputs** (`tuple[tuple[torch.FloatTensor]]`, *optional*) --
  Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`)
  `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of
  hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
- **past_key_values** (`~cache_utils.Cache`, *optional*) --
  Pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used to speed up sequential decoding. This typically consists in the `past_key_values`
  returned by the model at a previous stage of decoding, when `use_cache=True` or `config.use_cache=True`.

  Only [Cache](/docs/transformers/v5.4.0/ko/internal/generation_utils#transformers.Cache) instance is allowed as input, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
  If no `past_key_values` are passed, [DynamicCache](/docs/transformers/v5.4.0/ko/internal/generation_utils#transformers.DynamicCache) will be initialized by default.

  The model will output the same cache format that is fed as input.

  If `past_key_values` are used, the user is expected to input only unprocessed `input_ids` (those that don't
  have their past key value states given to this model) of shape `(batch_size, unprocessed_length)` instead of all `input_ids`
  of shape `(batch_size, sequence_length)`.
- **decoder_inputs_embeds** (`tuple[torch.FloatTensor]` of shape `(batch_size, target_sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded
  representation. If `past_key_values` is used, optionally only the last `decoder_inputs_embeds` have to be
  input (see `past_key_values`). This is useful if you want more control over how to convert
  `decoder_input_ids` indices into associated vectors than the model's internal embedding lookup matrix.

  If `decoder_input_ids` and `decoder_inputs_embeds` are both unset, `decoder_inputs_embeds` takes the value
  of `inputs_embeds`.
- **decoder_position_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0,
  config.n_positions - 1]`.

  [What are position IDs?](../glossary#position-ids)
- **labels** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Labels for computing the language modeling loss. Indices should either be in `[0, ..., config.vocab_size]`
  or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored (masked), the loss is
  only computed for the tokens with labels in `[0, ..., config.vocab_size]`. `sequence_length` should be smaller than or equal to `config.max_target_positions`.
- **use_cache** (`bool`, *optional*) --
  If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding (see
  `past_key_values`).0[Seq2SeqLMOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)`A [Seq2SeqLMOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([WhisperConfig](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperConfig)) and inputs.
The [WhisperForConditionalGeneration](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperForConditionalGeneration) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module`
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Language modeling loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`) -- Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
- **past_key_values** (`EncoderDecoderCache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`) -- It is a [EncoderDecoderCache](/docs/transformers/v5.4.0/ko/internal/generation_utils#transformers.EncoderDecoderCache) instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).

  Contains pre-computed hidden-states (key and values in the self-attention blocks and in the cross-attention
  blocks) that can be used (see `past_key_values` input) to speed up sequential decoding.
- **decoder_hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
- **decoder_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.
- **cross_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights of the decoder's cross-attention layer, after the attention softmax, used to compute the
  weighted average in the cross-attention heads.
- **encoder_last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) -- Sequence of hidden-states at the output of the last layer of the encoder of the model.
- **encoder_hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
- **encoder_attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the
  self-attention heads.

Example:

```python
>>> import torch
>>> from transformers import AutoProcessor, WhisperForConditionalGeneration
>>> from datasets import load_dataset

>>> processor = AutoProcessor.from_pretrained("openai/whisper-tiny.en")
>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en")

>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")

>>> inputs = processor(ds[0]["audio"]["array"], return_tensors="pt")
>>> input_features = inputs.input_features

>>> generated_ids = model.generate(inputs=input_features)

>>> transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
>>> transcription
' Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.'
```

**Parameters:**

config ([WhisperConfig](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperConfig)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.4.0/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[Seq2SeqLMOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or `tuple(torch.FloatTensor)``

A [Seq2SeqLMOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.Seq2SeqLMOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([WhisperConfig](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperConfig)) and inputs.

## WhisperForAudioClassification [[whisperforaudioclassification]][[transformers.WhisperForAudioClassification]]

#### transformers.WhisperForAudioClassification[[transformers.WhisperForAudioClassification]]

[Source](https://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/modeling_whisper.py#L1242)

Whisper Encoder Model with a sequence classification head on top (a linear layer over the pooled output) for tasks
like SUPERB Keyword Spotting.

This model inherits from [PreTrainedModel](/docs/transformers/v5.4.0/ko/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the
library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads
etc.)

This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#torch.nn.Module) subclass.
Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage
and behavior.

forwardtransformers.WhisperForAudioClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.4.0/src/transformers/models/whisper/modeling_whisper.py#L1269[{"name": "input_features", "val": ": torch.LongTensor | None = None"}, {"name": "encoder_outputs", "val": ": tuple[tuple[torch.FloatTensor]] | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "**kwargs", "val": ""}]- **input_features** (`torch.LongTensor` of shape `(batch_size, sequence_length, feature_dim)`, *optional*) --
  The tensors corresponding to the input audio features. Audio features can be obtained using
  [WhisperFeatureExtractor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor). See [WhisperFeatureExtractor.__call__()](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor.__call__) for details ([WhisperProcessor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperProcessor) uses
  [WhisperFeatureExtractor](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperFeatureExtractor) for processing audios).
- **encoder_outputs** (`tuple[tuple[torch.FloatTensor]]`, *optional*) --
  Tuple consists of (`last_hidden_state`, *optional*: `hidden_states`, *optional*: `attentions`)
  `last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) is a sequence of
  hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
- **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) --
  Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
  config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
  `config.num_labels > 1` a classification loss is computed (Cross-Entropy).0[SequenceClassifierOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)`A [SequenceClassifierOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([WhisperConfig](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperConfig)) and inputs.
The [WhisperForAudioClassification](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperForAudioClassification) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module`
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.

- **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided) -- Classification (or regression if config.num_labels==1) loss.
- **logits** (`torch.FloatTensor` of shape `(batch_size, config.num_labels)`) -- Classification (or regression if config.num_labels==1) scores (before SoftMax).
- **hidden_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) -- Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
  one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
- **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) -- Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
  sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
  heads.

Example:

```python
>>> import torch
>>> from transformers import AutoFeatureExtractor, WhisperForAudioClassification
>>> from datasets import load_dataset

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("sanchit-gandhi/whisper-medium-fleurs-lang-id")
>>> model = WhisperForAudioClassification.from_pretrained("sanchit-gandhi/whisper-medium-fleurs-lang-id")

>>> ds = load_dataset("google/fleurs", "all", split="validation", streaming=True)
>>> sample = next(iter(ds))

>>> inputs = feature_extractor(
...     sample["audio"]["array"], sampling_rate=sample["audio"]["sampling_rate"], return_tensors="pt"
... )
>>> input_features = inputs.input_features

>>> with torch.no_grad():
...     logits = model(input_features).logits

>>> predicted_class_ids = torch.argmax(logits).item()
>>> predicted_label = model.config.id2label[predicted_class_ids]
>>> predicted_label
'Afrikaans'
```

**Parameters:**

config ([WhisperForAudioClassification](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperForAudioClassification)) : Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the [from_pretrained()](/docs/transformers/v5.4.0/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[SequenceClassifierOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or `tuple(torch.FloatTensor)``

A [SequenceClassifierOutput](/docs/transformers/v5.4.0/ko/main_classes/output#transformers.modeling_outputs.SequenceClassifierOutput) or a tuple of
`torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various
elements depending on the configuration ([WhisperConfig](/docs/transformers/v5.4.0/ko/model_doc/whisper#transformers.WhisperConfig)) and inputs.