o wi@sddlmZmZmZddlZddlmZddlmZddl m Z m Z m Z ddl mZddlmZddlmZdd lmZmZdd lmZdd lmZdd lmZmZmZmZmZdd l m!Z!ddl"m#Z#m$Z$ddl%m&Z&ddl'm(Z(m)Z)m*Z*ddl+m,Z,m-Z-m.Z.ddl/m0Z0m1Z1m2Z2ddl3m4Z4m5Z5e*6e7Z8GdddeZ9Gdddej:Z;Gdddej:ZGdd d e0Z?Gd!d"d"eZ@e(Gd#d$d$e$ZAGd%d&d&eAZBGd'd(d(e1ZCGd)d*d*e4ZDe(d+d,Gd-d.d.eAeZEgd/ZFdS)0)CallableOptionalUnionN)ACT2FN)Cache DynamicCacheEncoderDecoderCache)PretrainedConfig)GenerationMixin)create_causal_mask)_prepare_4d_attention_mask#_prepare_4d_attention_mask_for_sdpa)FlashAttentionKwargs)GradientCheckpointingLayer)BaseModelOutputBaseModelOutputWithPast)BaseModelOutputWithPastAndCrossAttentionsSeq2SeqLMOutputSeq2SeqModelOutput)rope_config_validation)ALL_ATTENTION_FUNCTIONSPreTrainedModel)Unpack)auto_docstringcan_return_tuplelogging) GlmAttentionGlmRotaryEmbeddingapply_rotary_pos_emb)LlamaDecoderLayer LlamaModeleager_attention_forward) WhisperModelshift_tokens_rightcsheZdZdZdZdgZddddZ              dfdd ZZS)MoonshineConfiga" This is the configuration class to store the configuration of a [`MoonshineModel`]. It is used to instantiate a Moonshine 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 Moonshine [UsefulSensors/moonshine-tiny](https://huggingface.co/UsefulSensors/moonshine-tiny). Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 32768): Vocabulary size of the Moonshine model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MoonshineModel`]. hidden_size (`int`, *optional*, defaults to 288): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 1152): Dimension of the MLP representations. encoder_num_hidden_layers (`int`, *optional*, defaults to 6): Number of hidden layers in the Transformer encoder. decoder_num_hidden_layers (`int`, *optional*, defaults to 6): Number of hidden layers in the Transformer decoder. encoder_num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer encoder. decoder_num_attention_heads (`int`, *optional*, defaults to 8): Number of attention heads for each attention layer in the Transformer decoder. encoder_num_key_value_heads (`int`, *optional*): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `encoder_num_key_value_heads=encoder_num_attention_heads`, the model will use Multi Head Attention (MHA), if `encoder_num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`. decoder_num_key_value_heads (`int`, *optional*): This is the number of key_value heads that should be used to implement Grouped Query Attention. If `decoder_num_key_value_heads=decoder_num_attention_heads`, the model will use Multi Head Attention (MHA), if `decoder_num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `decoder_num_attention_heads`. pad_head_dim_to_multiple_of (`int`, *optional*): Pad head dimension in encoder and decoder to the next multiple of this value. Necessary for using certain optimized attention implementations. encoder_hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder. decoder_hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 512): The maximum sequence length that this model might ever be used with. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. decoder_start_token_id (`int`, *optional*, defaults to 1): Corresponds to the "<|startoftranscript|>" token, which is automatically used when no `decoder_input_ids` are provided to the `generate` function. It is used to guide the model`s generation process depending on the task. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). rope_theta (`float`, *optional*, defaults to 10000.0): The base period of the RoPE embeddings. rope_scaling (`Dict`, *optional*): Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value accordingly. Expected contents: `rope_type` (`str`): The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope', 'llama3'], with 'default' being the original RoPE implementation. `factor` (`float`, *optional*): Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In most scaling types, a `factor` of x will enable the model to handle sequences of length x * original maximum pre-trained length. `original_max_position_embeddings` (`int`, *optional*): Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during pretraining. `attention_factor` (`float`, *optional*): Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention computation. If unspecified, it defaults to value recommended by the implementation, using the `factor` field to infer the suggested value. `beta_fast` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear ramp function. If unspecified, it defaults to 32. `beta_slow` (`float`, *optional*): Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear ramp function. If unspecified, it defaults to 1. `short_factor` (`list[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to short contexts (< `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 `long_factor` (`list[float]`, *optional*): Only used with 'longrope'. The scaling factor to be applied to long contexts (< `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden size divided by the number of attention heads divided by 2 `low_freq_factor` (`float`, *optional*): Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE `high_freq_factor` (`float`, *optional*): Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE partial_rotary_factor (`float`, *optional*, defaults to 0.9): Percentage of the query and keys which will have rotary embedding. is_encoder_decoder (`bool`, *optional*, defaults to `True`): Whether the model is used as an encoder/decoder or not. attention_bias (`bool`, *optional*, defaults to `False`): Whether to use a bias in the query, key, value and output projection layers during self-attention. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. bos_token_id (`int`, *optional*, defaults to 1): Denotes beginning of sequences token id. eos_token_id (`int`, *optional*, defaults to 2): Denotes end of sequences token id. Example: ```python >>> from transformers import MoonshineModel, MoonshineConfig >>> # Initializing a Moonshine style configuration >>> configuration = MoonshineConfig().from_pretrained("UsefulSensors/moonshine-tiny") >>> # Initializing a model from the configuration >>> model = MoonshineModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` moonshinepast_key_valuesencoder_num_key_value_headsencoder_num_attention_headsencoder_num_hidden_layers)num_key_value_headsnum_attention_headsnum_hidden_layers Ngelusilu{Gz?T@?Frc s||_||_||_||_||_||_||_|dur|}||_| dur$|} | |_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_||_||_t|tjd||||d|dS)N) bos_token_id eos_token_idis_encoder_decoderdecoder_start_token_id) vocab_size hidden_sizeintermediate_sizer+decoder_num_hidden_layersr*decoder_num_attention_headsr)decoder_num_key_value_headspad_head_dim_to_multiple_ofencoder_hidden_actdecoder_hidden_actmax_position_embeddingsinitializer_ranger? use_cache rope_theta rope_scalingpartial_rotary_factorr>attention_biasattention_dropoutrsuper__init__)selfrArBrCr+rDr*rEr)rFrGrHrIrJrKr?rLrMrNrOr>rPrQr<r=kwargs __class__r@l/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/transformers/models/moonshine/modular_moonshine.pyrSsF zMoonshineConfig.__init__)r/r0r1r2r2r3r3NNNr4r5r6r7r8Tr9Nr:TFr;r8r) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_maprS __classcell__r@r@rVrXr&/sB}r&c2eZdZfddZdejdejfddZZS)MoonshineEncoderMLPcsBt||_t||_t|j|j|_ t|j|j|_ dSN rRrSconfigr activation_fnnnLinearrBrCfc1fc2rTre hidden_actrVr@rXrSs  zMoonshineEncoderMLP.__init__ hidden_statesreturncCs"||}||}||}|Src)rirfrj)rTrmr@r@rXforwards   zMoonshineEncoderMLP.forwardrYrZr[rStorchTensorror`r@r@rVrXrb rbcra)MoonshineDecoderMLPcsFt||_t||_t|j|jd|_ t|j|j|_ dS)NrrdrkrVr@rXrS s  zMoonshineDecoderMLP.__init__rmrncCs8||}|jddd\}}|||}||}|S)Nr)dim)richunkrfrj)rTrmgater@r@rXros  zMoonshineDecoderMLP.forwardrpr@r@rVrXrt rsrtcseZdZdededededef fdd Z     dd ejd e e ejejfd e ejd e e d e ej de ejde ede eje eje e ejffddZZS)MoonshineAttentionre layer_idx is_causalr-r,cs~|||dt||||_t|d|j|j|_|jj dur:|jj }||j|d|}||j|_ dSd|_ dS)N)r-r,head_dimr8r) updaterRrSr{getattrrBr-r|rerGhead_dim_padding)rTrerzr{r-r,target_multipletarget_head_dimrVr@rXrSs  zMoonshineAttention.__init__Nrmposition_embeddingsattention_maskpast_key_valuecache_positionkey_value_statesrUrncKsZ|jdd\}} |||| |jj|jdd} |du} |dur9|j|j } | r6d|j|j <|j }n|j }|dur?|n|} | rT|rT| rT|j |j }|j |j }n7|| |d|jj|jdd}|| |d|jj|jdd}| r|dur||||j d|i\}}| s|\}}t| |||\} }|dur|||d}||||j |\}}t}|jjdkrt|jj}|jr|dur| dkrdnd}|jd krtjj| d |jf} tjj|d |jf}tjj|d |jf}||| |||f|jsd n|j|j|d |\}}|jd kr|d d|j f}||| d}| |}||fS) Nrur8rTr)sincosreagerFrr;)dropoutscalingr{.)!shapeq_projviewrer,r| transpose is_updatedgetrzcross_attention_cacheself_attention_cache key_cache value_cachek_projv_projr}r r#_attn_implementationrr{rrqrg functionalpadtrainingrQrreshape contiguouso_proj)rTrmrrrrrrUbszq_len query_statesis_cross_attentionrcurrent_states key_states value_statesrr cache_kwargsattention_interfacer{ attn_output attn_weightsr@r@rXro1sx "           zMoonshineAttention.forward)NNNNN)rYrZr[r&intboolrSrqrrrtupler LongTensorrrror`r@r@rVrXrysD ryc@s eZdZdS)MoonshineRotaryEmbeddingN)rYrZr[r@r@r@rXrsrcs&eZdZdedeffdd ZZS)MoonshineEncoderLayerrerzcs\t||t||d|j|jd|_t||j|_t j |j dd|_ t j |j dd|_ dS)NFrerzr{r-r,bias)rRrSryr*r) self_attnrbrHmlprg LayerNormrBinput_layernormpost_attention_layernormrTrerzrVr@rXrSszMoonshineEncoderLayer.__init__)rYrZr[r&rrSr`r@r@rVrXrsrc seZdZddedeeffdd Z           ddejdeejd eejd eejd eej d eej d ee dee dee deej dee ejejfdee ejejfde ej ee ej ej fffddZZS)MoonshineDecoderLayerNrerzcst|j|_t||d|j|jd|_t||d|j|jd|_t||j |_ t j |jdd|_ t j |jdd|_t j |jdd|_dS)NTrFr)rRrSrBryrErFr encoder_attnrtrIrrgrrrfinal_layernormrrVr@rXrSs( zMoonshineDecoderLayer.__init__Frmrencoder_hidden_statesencoder_attention_mask position_idsencoder_position_idsroutput_attentionsrLrrencoder_position_embeddingsrnc  Ks|}||}|jd|||||| | | d| \}}||}d}|dur<|}||}|j|||||| d\}}||}|}||}||}||}|f}|rW|||f7}|S)N)rmrrrrrLrr)rmrrrrrLr@)rrrrrr)rTrmrrrrrrrrLrrrrUresidualself_attn_weightscross_attn_weightsoutputsr@r@rXrosH        zMoonshineDecoderLayer.forwardrc) NNNNNNFFNNN)rYrZr[r&rrrSrqrrrrrr FloatTensorror`r@r@rVrXrsP     rc@sLeZdZeZdZdZdZddgZdZ dZ dZ dZ ddZ dejfd d Zd S) MoonshinePreTrainedModelmodel input_valuesTrrcCs|jj}t|tjtjfr%|jjjd|d|j dur#|j j dSdSt|tj tj frD|jj d|j durB|j j dSdSt|tjrc|jjjd|d|jdure|jj|j dSdSdS)Nr;)meanstdg?)rerK isinstancergrhConv1dweightdatanormal_rzero_ GroupNormrfill_ Embedding padding_idx)rTmodulerr@r@rX _init_weightss"    z&MoonshinePreTrainedModel._init_weights input_lengthscCs@t|ddd}t|ddd}t|ddd}|S)zH Computes the output length of the convolutional layers @r8rr)r)rTroutput_conv1_lengthoutput_conv2_lengthoutput_conv3_lengthr@r@rX _get_feat_extract_output_lengthssz9MoonshinePreTrainedModel._get_feat_extract_output_lengthsN)rYrZr[r& config_classbase_model_prefixmain_input_namesupports_gradient_checkpointing_no_split_modules_supports_flash_attn_2_supports_sdpa_supports_cache_class_supports_static_cacherrqrrr@r@r@rXrsrcseZdZdZdZdeffdd ZdejfddZ d ejfd d Z e dde e jd e e jde ede edeedef ddZZS)MoonshineEncoderz Transformer encoder consisting of *config.num_hidden_layers* layers. Each layer is a [`MoonshineEncoderLayer`] Args: config: MoonshineConfig rrecst|_j}tjd|dddd|_tj|d|ddd |_tjd||ddd |_tj d|d d |_ t d |_ t fd dtjD|_tj|dd|_d|_|dS)Nr8rrF) kernel_sizestriderrrr)rrgh㈵>) num_groups num_channelsepsrecg|]}t|qSr@)r.0idxrr@rX 3z-MoonshineEncoder.__init__..r)rRrSrerBrgrconv1conv2conv3r groupnormr rotary_emb ModuleListranger+layersr layer_normgradient_checkpointing post_init)rTre embed_dimrVrrXrS&s   zMoonshineEncoder.__init__rncC|jSrcrrTr@r@rXget_input_embeddings:z%MoonshineEncoder.get_input_embeddingsvaluecC ||_dSrcr)rTrr@r@rXset_input_embeddings= z%MoonshineEncoder.set_input_embeddingsNrroutput_hidden_statesflash_attn_kwargscKs|dur|n|jj}|dur|n|jj}|durtd|d}tj||}| |}tj | |}tj | |}| ddd}|dur||jd}d}|ddd|fdd|f}|jjd krv|d krs|nd}n|jjd kr|st||j}nt||j}tjd|jd|jd d} ||| } |rd nd} |rd nd} |jD]#} |r| |f7} | |f|| || d|}|d}|r| |df7} q||}|r| |f7} t|| | dS)a Args: input_values (`torch.FloatTensor` of shape `(batch_size, audio_length)`): Float values of the raw speech waveform. Raw speech waveform can be obtained by loading a `.flac` or `.wav` audio file into an array of type `list[float]` or a `numpy.ndarray`, *e.g.* via the soundfile library (`pip install soundfile`). To prepare the array into `input_values`, the [`AutoFeatureExtractor`] should be used for padding and conversion into a tensor of type `torch.FloatTensor`. attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*): Mask to avoid performing attention on padding indices in `input_values`. 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) output_attentions (`bool`, *optional*): Whether or not to return the attentions tensors of all attention layers. See `attentions` under returned tensors for more detail. output_hidden_states (`bool`, *optional*): Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors for more detail. return_dict (`bool`, *optional*): Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple. NzYou must specify input_values.r8rrru.flash_attention_2r;sdpadevicer@)rrrrlast_hidden_staterm attentions)rerr  ValueError unsqueezergrtanhrrr4rrpermuterrranyrdtyper rqarangerrrrr)rTrrrr r rmmask_lendownsample_striderrall_hidden_statesall_self_attns encoder_layer layer_outputsr@r@rXro@sb            zMoonshineEncoder.forward)NNNN)rYrZr[r\rr&rSrgModulerr rrrqrrrrrrrror`r@r@rVrXrs0rcseZdZdZdeffdd Z           ddeejdeej deejdee d eej d ee d ee d ee d eejdeej deej de edeeeffddZZS)MoonshineDecoder input_idsrecsBttjjdd|_tfddtjD|_ dS)NFrcrr@)rrrr@rXrrz-MoonshineDecoder.__init__..) rRrSrgrrBnormrrrDrrTrerVrrXrSs  zMoonshineDecoder.__init__Nrrr( inputs_embedsrLrr rrrr rnc  Ksz|dur|n|jj}|dur|n|jj}|dur|n|jj}|du|duAr*td|jr9|jr9|r9tdd}|durB| |}|rS|durSt } t }t | |}| duro|dur_| nd}t j|||jd|jd} |durx| d}t|j||| ||d}|}|||}|rd nd}|rd nd}|r| durd nd}| dur| jd }d }| d dd|fd d|f} |jjd kr| dkr| nd} n|jjdkr|st| |j|jd } n t| |j|jd } |jD]5}|r||f7}|||| f| ||||| |d| }|d}|r!||df7}| dur!||df7}q||}|r/||f7}t||r6|nd|||dS)a encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*): Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. encoder_attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*): Mask to avoid performing attention on padding indices in `encoder_hidden_states`. 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) Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.Frr8r)re input_embedsrrr(rr@r .rr;r)rrrrrLrrr)rr(rmrcross_attentions)rerr rLrrrlogger warning_once embed_tokensrr get_seq_lengthrqrrrrr rrrrrr rr%r)rTr$rrr(r'rLrr rrrr rrpast_seen_tokens causal_maskrmrrrall_cross_attentionsrr decoder_layerr!r@r@rXros                zMoonshineDecoder.forward) NNNNNNNNNNN)rYrZr[rr&rSrrqrrrrrrrrrrrror`r@r@rVrXr#sR       r#c@seZdZee            ddeejdeejdeejdeejdee e ejdee e e ejfdee ejd ee ejd ee d ee d ee d eejde fddZdS)MoonshineModelNrrdecoder_input_idsdecoder_attention_maskencoder_outputsr(decoder_inputs_embedsdecoder_position_idsrLrr rrnc  Cs| dur| n|jj} | dur| n|jj} | dur| n|jj} |dur,|j||| | d}n"t|tsNt|dt|dkr?|dndt|dkrJ|dndd}|j||||j |||| | | | d } t | j | j | j | j | j|j |j |j dS) ad input_values (`torch.FloatTensor` of shape `(batch_size, audio_length)`): Float values of the raw speech waveform. Raw speech waveform can be obtained by loading a `.flac` or `.wav` audio file into an array of type `list[float]` or a `numpy.ndarray`, *e.g.* via the soundfile library (`pip install soundfile`). To prepare the array into `input_values`, the [`AutoFeatureExtractor`] should be used for padding and conversion into a tensor of type `torch.FloatTensor`. decoder_input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`): Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it. Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input IDs?](../glossary#input-ids) decoder_attention_mask (`torch.Tensor` 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) Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`). If you want to change padding behavior, you should read [`modeling_opt._prepare_decoder_attention_mask`] and modify to your needs. See diagram 1 in [the paper](https://huggingface.co/papers/1910.13461) for more information on the default strategy. - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. decoder_inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*): Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded representation. 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. 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) Example: ```python >>> import torch >>> from transformers import AutoFeatureExtractor, MoonshineModel >>> from datasets import load_dataset >>> model = MoonshineModel.from_pretrained("UsefulSensors/moonshine-tiny") >>> feature_extractor = AutoFeatureExtractor.from_pretrained("UsefulSensors/moonshine-tiny") >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation") >>> inputs = feature_extractor(ds[0]["audio"]["array"], return_tensors="pt") >>> input_values = inputs.input_values >>> decoder_input_ids = torch.tensor([[1, 1]]) * model.config.decoder_start_token_id >>> last_hidden_state = model(input_values, decoder_input_ids=decoder_input_ids).last_hidden_state >>> list(last_hidden_state.shape) [1, 2, 288] ``` N)rrr rr8rr) r$rrrr(r'rrLrr r)rr(decoder_hidden_statesdecoder_attentionsr*encoder_last_hidden_staterencoder_attentions)rerr rLencoderrrlendecoderrrr(rmrr*)rTrrr4r5r6r(r7r8rLrr rdecoder_outputsr@r@rXro;sPP zMoonshineModel.forward) NNNNNNNNNNNN)rYrZr[rrrrqrrrrr rrror@r@r@rXr3:sT      r3zj The Moonshine Model with a language modeling head. Can be used for automatic speech recognition. ) custom_introcs"eZdZdgZdeffdd ZddZddZd d Zd d Z d e j fddZ e e             d deejdeejdeejdeejdeeeejdeeeeejfdeeejdeeejdeedeedeedeejdeejd efddZZS)!!MoonshineForConditionalGenerationzproj_out.weightrecs8t|t||_tj|j|jdd|_| dS)NFr) rRrSr3rrgrhrBrAproj_outrr&rVr@rXrSs   z*MoonshineForConditionalGeneration.__init__cC |jSrc)r get_encoderrr@r@rXrEr z-MoonshineForConditionalGeneration.get_encodercCrDrc)r get_decoderrr@r@rXrFr z-MoonshineForConditionalGeneration.get_decodercCrrcrCrr@r@rXget_output_embeddingsrz7MoonshineForConditionalGeneration.get_output_embeddingscCrrcrG)rTnew_embeddingsr@r@rXset_output_embeddingsr z7MoonshineForConditionalGeneration.set_output_embeddingsrncCrDrc)rrrr@r@rXrr z6MoonshineForConditionalGeneration.get_input_embeddingsNrrr4r5r6r(r7r8rLrr rlabelscCs| dur|dur|durt| |jj|jj}|j||||||||| | | | d }||j}d}| dur=|j|| |jjd}t |||j |j |j |j |j|j|jd S)a' input_values (`torch.FloatTensor` of shape `(batch_size, audio_length)`): Float values of the raw speech waveform. Raw speech waveform can be obtained by loading a `.flac` or `.wav` audio file into an array of type `list[float]` or a `numpy.ndarray`, *e.g.* via the soundfile library (`pip install soundfile`). To prepare the array into `input_values`, the [`AutoFeatureExtractor`] should be used for padding and conversion into a tensor of type `torch.FloatTensor`. decoder_input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`): Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it. Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. [What are input IDs?](../glossary#input-ids) decoder_attention_mask (`torch.Tensor` 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) Indices can be obtained using [`AutoTokenizer`]. See [`PreTrainedTokenizer.encode`] and [`PreTrainedTokenizer.__call__`] for details. If `past_key_values` is used, optionally only the last `decoder_input_ids` have to be input (see `past_key_values`). If you want to change padding behavior, you should read [`modeling_opt._prepare_decoder_attention_mask`] and modify to your needs. See diagram 1 in [the paper](https://huggingface.co/papers/1910.13461) for more information on the default strategy. - 1 indicates the head is **not masked**, - 0 indicates the head is **masked**. decoder_inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*): Optionally, instead of passing `decoder_input_ids` you can choose to directly pass an embedded representation. 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. 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]`. Example: ```python >>> import torch >>> from transformers import AutoProcessor, MoonshineForConditionalGeneration >>> from datasets import load_dataset >>> processor = AutoProcessor.from_pretrained("UsefulSensors/moonshine-tiny") >>> model = MoonshineForConditionalGeneration.from_pretrained("UsefulSensors/moonshine-tiny") >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation") >>> inputs = processor(ds[0]["audio"]["array"], return_tensors="pt") >>> input_values = inputs.input_values >>> generated_ids = model.generate(input_values, max_new_tokens=100) >>> 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.' ```N) rr4r6r5r(r7r8rLrr r)logitsrKrA) lossrLr(r9r:r*r;rr<)r%re pad_token_idr?rrCr loss_functionrArr(r9r:r*r;rr<)rTrrr4r5r6r(r7r8rLrr rrKrrLrMr@r@rXrosDY z)MoonshineForConditionalGeneration.forward) NNNNNNNNNNNNN)rYrZr[_tied_weights_keysr&rSrErFrHrJrgr"rrrrrqrrrrr rrror`r@r@rVrXrBsh      rB)r&r3rrB)Gtypingrrrrqtorch.nnrg activationsr cache_utilsrrr configuration_utilsr generationr masking_utilsr modeling_attn_mask_utilsr rmodeling_flash_attention_utilsrmodeling_layersrmodeling_outputsrrrrrmodeling_rope_utilsrmodeling_utilsrrprocessing_utilsrutilsrrrglm.modeling_glmrrr llama.modeling_llamar!r"r#whisper.modeling_whisperr$r% get_loggerrYr+r&r"rbrtryrrrrrr#r3rB__all__r@r@r@rXsT          NnX%