UhddlmZmZmZmZddlZddlmZddlm Z ddl m Z m Z m Z ddlmZddlmZddlmZmZdd lmZdd lmZdd lmZmZmZmZmZdd lm Z dd l!m"Z"m#Z#ddl$m%Z%ddl&m'Z'm(Z(m)Z)ddl*m+Z+m,Z,m-Z-ddl.m/Z/m0Z0m1Z1ddl2m3Z3m4Z4e)jje6Z7GddeZ8GddejrZ:GddejrZ;Gdde+Z<Gdde,Z=Gdde/Z>Gd d!eZ?e'Gd"d#e#Z@Gd$d%e@ZAGd&d'e0ZBGd(d)e3ZCe'd*+Gd,d-e@eZDgd.ZEy)/)CallableOptionalTupleUnionN)ACT2FN)Cache DynamicCacheEncoderDecoderCache)PretrainedConfig)GenerationMixin)_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_rightcjeZdZdZdZdgZddddZ d fd ZxZS) 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 checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). 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 checkout [this paper](https://arxiv.org/pdf/2305.13245.pdf). 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_layersc ||_||_||_||_||_||_||_||}||_| |} | |_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_||_||_||_||_t-|t/|`d||||d|y)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_ranger5 use_cache rope_theta rope_scalingpartial_rotary_factorr4attention_biasattention_dropoutrsuper__init__)selfr7r8r9r-r:r,r;r+r<r=r>r?r@rAr5rBrCrDrEr4rFrGr2r3kwargs __class__s /var/www/catia.catastroantioquia-mas.com/valormas/lib/python3.12/site-packages/transformers/models/moonshine/modular_moonshine.pyrIzMoonshineConfig.__init__s8%&!2)B&)B&+F(+F( & .*E '+F( & .*E '+F(+F("4"4'>$!2&<#"$(%:""4,!2 t$  %%1#9    )ii irOrPNNNgelusiluig{Gz?Tg@Ng?TFrSr) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_maprI __classcell__rLs@rMr(r(.s{ zJ#4"5<<8M"#"#$%$%$($($(!! # !3D D rNr(cVeZdZfdZdej dej fdZxZS)MoonshineEncoderMLPct|||_t||_t j |j|j|_ t j |j|j|_ yN rHrIconfigr activation_fnnnLinearr8r9fc1fc2rJrc hidden_actrLs rMrIzMoonshineEncoderMLP.__init__s^  #J/99V//1I1IJ99V55v7I7IJrN hidden_statesreturncl|j|}|j|}|j|}|Sra)rgrdrh)rJrks rMforwardzMoonshineEncoderMLP.forwards4/ **=9 / rNrUrVrWrItorchTensorrnr\r]s@rMr_r_s$KU\\ellrNr_cVeZdZfdZdej dej fdZxZS)MoonshineDecoderMLPct|||_t||_t j |j|jdz|_ t j |j|j|_ y)Nrrbris rMrIzMoonshineDecoderMLP.__init__ sc  #J/99V//1I1IA1MN99V55v7I7IJrNrkrlc|j|}|jdd\}}|j||z}|j|}|S)Nr)dim)rgchunkrdrh)rJrkgates rMrnzMoonshineDecoderMLP.forwardsS/ +11!1< t**40=@ / rNror]s@rMrsrs s$KU\\ellrNrscheZdZdededededef fd Z ddejde e ejejfd e ejd e e d e ejd e ejd e ede eje eje e ejffdZxZS)MoonshineAttentionrc layer_idx is_causalr/r.cn|j||dt| ||||_t |d|j |j z|_|jjC|jj}||j|zdz |zz}||jz |_ yd|_ y)N)r/r.head_dimrSr) updaterHrIr}getattrr8r/rrcr=head_dim_padding) rJrcr|r}r/r.target_multipletarget_head_dimrLs rMrIzMoonshineAttention.__init__s  .AZmno +" F4F4F&JdJd4de  ;; 2 2 >"kkEEO-$--/2QTU2UZi1ijO$3dmm$CD !$%D !rNrkposition_embeddingsattention_maskpast_key_valuecache_positionkey_value_statesrKrlc |jdd\}} |j|j|| |jj|j j dd} |du} |Y|jj|j} | r&d|j|j<|j}n |j}||n|} | r7|r5 r3|j|j}|j|j}n|j| j|d|jj|j j dd}|j| j|d|jj|j j dd}| r%|#|j!|||jd|i\}}| s?|\}}t#| |||\} }|'|||d}|j!|||j|\}}t$}|jj&dk7r^|jj&dk(r(|jd d rt(j+d nt,|jj&}|j.r || dkDrdnd }|j0d kDrt2j4j6j9| d |j0f} t2j4j6j9|d |j0f}t2j4j6j9|d |j0f}||| |||f|j:sd n |j<|j>|d|\}}|j0d kDr|dd|j0 f}|jA|| djC}|jE|}||fS)NrvrSrTr)sincosreagersdpaoutput_attentionsFz`torch.nn.functional.scaled_dot_product_attention` does not support `output_attentions=True`. Falling back to eager attention. This warning can be removed using the argument `attn_implementation="eager"` when loading the model.rrT)dropoutscalingr}.)#shapeq_projviewrcr.r transpose is_updatedgetr|cross_attention_cacheself_attention_cache key_cache value_cachek_projv_projrr!r$_attn_implementationlogger warning_oncerr}rrpre functionalpadtrainingrGrreshape contiguouso_proj)rJrkrrrrrrKbszq_len query_statesis_cross_attentionrcurrent_states key_states value_statesrr cache_kwargsattention_interfacer} attn_output attn_weightss rMrnzMoonshineAttention.forward0s#(("- U KK & + +C 8W8WY]YfYf g q qrsuv w .T9  %'2266t~~FJ!<@))$..9!/!E!E!/!D!D.>-I)} .Z'11$..AJ)55dnnEL N+c2t{{>> N1a   N+c2t{{>> N1a  "n&@+9+@+@ dnn?OQ_>`,( L"*HC';L*VY[^'_ $L*)'*3.Y +9+@+@ dnnl,( L)@ ;; + +w 6{{//69fjjI\^c>d##L '>dkk>^>^&_# NN~/E%RS)DY^  1 $ 88..22Q5RR S[)rNr{c eZdZy)MoonshineRotaryEmbeddingN)rUrVrWr6rNrMrrsrNrc(eZdZdedeffd ZxZS)MoonshineEncoderLayerrcr|cFt|||t||d|j|j|_t ||j|_tj|jd|_ tj|jd|_ y)NFrcr|r}r/r.bias)rHrIr{r,r+ self_attnr_r>mlpre LayerNormr8input_layernormpost_attention_layernormrJrcr|rLs rMrIzMoonshineEncoderLayer.__init__s ++ & B B & B B  'vv/H/HI!||F,>,>UK(* V5G5Ge(T%rN)rUrVrWr(rrIr\r]s@rMrrs U U3 U UrNrc eZdZddedeeffd Z ddejdeejdeejdeejdeejd eejd ee d ee d ee d eejdee ejejfdee ejejfde ejee ejejfffdZxZS)MoonshineDecoderLayerrcr|ct||j|_t||d|j|j |_t||d|j|j |_t||j|_ tj|jd|_ tj|jd|_tj|jd|_y)NTrFr)rHrIr8r{r;r<r encoder_attnrsr?rrerrrfinal_layernormrs rMrIzMoonshineDecoderLayer.__init__s !--+ & B B & B B  / & B B & B B  'vv/H/HI!||F,>,>UK(* V5G5Ge(T%!||F,>,>UKrNrkrencoder_hidden_statesencoder_attention_mask position_idsencoder_position_idsrrrBrrencoder_position_embeddingsrlc H|}|j|}|jd|||||| | | d| \}}||z}d}|2|}|j|}|j|||||| \}}||z}|}|j |}|j |}||z}|f}|r|||fz }|S)N)rkrrrrrBrr)rkrrrrrBr6)rrrrrr)rJrkrrrrrrrrBrrrrKresidualself_attn_weightscross_attn_weightsoutputss rMrnzMoonshineDecoderLayer.forwards !,,]; ,:4>> , ')%)/) 3 ,  , ( (!=0 " ,$H 99-HM040A0A+!65-"3# 1B1 -M-%}4M!,,]; /  =0  "  )+=> >GrNra) NNNNNNFFNNN)rUrVrWr(rrrIrprqrr rr FloatTensorrnr\r]s@rMrrsjLL8C=L6268<9=37;?*.,1$)59KOSW<||<!.< ( 5 < !) 6 < u//0 <'u'7'78<!<$D><D><!!1!12<&eELL%,,,F&GH<&.eELL%,,4N.O%P< u  (51B1BEDUDU1U+V"WW X<rNrcZeZdZeZdZdZdZddgZdZ dZ dZ dZ dZ dejfdZy ) MoonshinePreTrainedModelmodel input_valuesTrrc8|jj}t|tjtj frY|j jjd||j%|jjjyyt|tjtjfrW|j jjd|j%|jjjyyt|tjrf|j jjd||j2|j j|jjyyy)NrT)meanstdg?)rcrA isinstancererfConv1dweightdatanormal_rzero_ GroupNormrfill_ Embedding padding_idx)rJmodulers rM _init_weightsz&MoonshinePreTrainedModel._init_weightss kk++ fryy"))4 5 MM   & &CS & 9{{&   &&(' r|| < = MM   $ $S ){{&   &&('  - MM   & &CS & 9!!- ""6#5#56<<>..rN input_lengthsc~t|dz dz dz}t|dz dz dz}t|dz dz dz}|S)zH Computes the output length of the convolutional layers @rSrr)r)rJroutput_conv1_lengthoutput_conv2_lengthoutput_conv3_lengths rM _get_feat_extract_output_lengthsz9MoonshinePreTrainedModel._get_feat_extract_output_lengthssZ"=3#6""N>N#rNrceZdZdZdZdeffd ZdejfdZ dejfdZ e dde e jd e e jd e ed e ed eedef d ZxZS)MoonshineEncoderz Transformer encoder consisting of *config.num_hidden_layers* layers. Each layer is a [`MoonshineEncoderLayer`] Args: config: MoonshineConfig rrcc bt||||_|j}t j d|ddd|_t j |d|zdd |_t j d|z|dd |_t jd|d |_ t| |_ t jt|jDcgc]}t!||c}|_t j$|d |_d|_|j+ycc}w)NrSrrF) kernel_sizestriderrrr)rrgh㈵>) num_groups num_channelseps)rcr)rHrIrcr8rerconv1conv2conv3r groupnormr rotary_emb ModuleListranger-rlayersr layer_normgradient_checkpointing post_init)rJrc embed_dimidxrLs rMrIzMoonshineEncoder.__init__+s   && YYq)ReT YYy!i-QqQ YYq9}iQqQ PTU2&Amm;@AaAa;b cC "63 / c  ,,yu=&+#  dsD,rlc|jSrarrJs rMget_input_embeddingsz%MoonshineEncoder.get_input_embeddings?s zzrNvaluec||_yrar)rJrs rMset_input_embeddingsz%MoonshineEncoder.set_input_embeddingsBs  rNrroutput_hidden_statesflash_attn_kwargsc ||n|jj}||n|jj}| td|j d}t j j|j|}|j|}t j j|j|}t j j|j|}|jddd}||j|jd}d}|ddd|fdd|f}|jj d k(r|d k(j#r|nd}nH|jj d k(r|st%||j&}nt)||j&}t+j,d|jd|j. j d} |j1|| } |rd nd} |rd nd} |j2D])} |r| |fz } | |f|| || d|}|d}|s!| |dfz } +|j5|}|r| |fz } t7|| | S)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.rSrrrv.flash_attention_2rTrdevicer6)rrrrlast_hidden_staterk attentions)rcrr ValueError unsqueezerertanhrrrQrrpermuterrranyrdtyperrparangerrrrr)rJrrrrrrkmask_lendownsample_striderrall_hidden_statesall_self_attns encoder_layer layer_outputss rMrnzMoonshineEncoder.forwardEs>2C1N-TXT_T_TqTq$8$D $++JjJj   => >$--a0  **4::l+CD }5  **4::m+DE  **4::m+DE %--aA6   %<<^=Q=QRT=UVH * +C1D3D1D,DEc9H9nUN{{//3FF4Bc4I3N3N3PVZ11V;DU!D^UbUhUh!i" c 'tn c $$89 c  !c c rNrcZeZdZdZdeffd Z ddeejdeejdeejdee deejdee d ee d ee d eejd eejd eejde edeeeffdZxZS)MoonshineDecoder input_idsrcc t||tj|jd|_tj t|jDcgc]}t||c}|_ ycc}wNFr) rHrIrerr8normrrr:rr)rJrcr rLs rMrIzMoonshineDecoder.__init__s\  LL!3!3%@ mm;@AaAa;b cC "63 / c  csA=rrr* inputs_embedsrBrrrrrrrlc  $||n|jj}||n|jj}||n|jj}|du|duz r t d|j r%|j r|rtjdd}||j|}|r"| t} t}t| |}| F||jnd}tj|||jdz|j } || j#d}|j%||| ||}|}|j'||}|rdnd}|rdnd}|r| dnd}| | jd }d }| d dd|fd d|f} |jj(d k(r| d k(j+r| nd} nd|jj(dk(r'|s%t-| |j.|jd } n$t1| |j.|jd } |j2D]:}|r||fz }||f|| | ||||| |d | }|d}|s&||dfz }| 2||dfz }<|j5|}|r||fz }t7||r|nd|||S)a encoder_hidden_states (`torch.FloatTensor` of shape `(batch_size, encoder_sequence_length, hidden_size)`, *optional*): Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder. encoder_attention_mask (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*): Mask to avoid performing attention on padding indices in `encoder_hidden_states`. Mask values selected in `[0, 1]`: - 1 for tokens that are **not masked**, - 0 for tokens that are **masked**. [What are attention masks?](../glossary#attention-mask) Nz:You must specify exactly one of input_ids or inputs_embedszX`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.FrrSrr6r.rrTr) rrrrrrrBrrr)rr*rkrcross_attentions)rcrrrBrr rrr embed_tokensr r get_seq_lengthrpr$rrr_update_causal_maskrrr"rr#rrr1r)rJr.rrr*r2rBrrrrrrrrpast_seen_tokens causal_maskrkrr'r(all_cross_attentionsr%r& decoder_layerr*s rMrnzMoonshineDecoder.forwardsF22C1N-TXT_T_TqTq$8$D $++JjJj "+!6IDKK $0N !12FH]^O  !CRC^==?de "\\ "2]5H5H5K"KTaThThN  )33A6L.. M>?L] & #oom\J#7BD0d&7A $D>A 'tnA !!1!12A  ((9(9:A !) 6A $$89A  u-- .A rNr-ceZdZee ddeejdeejdeejdeejdee e ejdee e e ejfdee ejd ee ejd ee d ee d ee d eejde fdZy)MoonshineModelNrrdecoder_input_idsdecoder_attention_maskencoder_outputsr*decoder_inputs_embedsdecoder_position_idsrBrrrrlc n| | n|jj} | | n|jj} | | n|jj} ||j ||| | }nGt |t s7t |dt|dkDr|dndt|dkDr|dnd}|j||||j|||| | | |  } t| j| j| j| j| j|j|j|jS) 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://arxiv.org/abs/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)rrrrrSrr) r.rrrr*r2rrBrrr)rr*decoder_hidden_statesdecoder_attentionsr5encoder_last_hidden_staterencoder_attentions)rcrrrBencoderrrlendecoderrrr*rkrr5)rJrrr?r@rAr*rBrCrBrrrdecoder_outputss rMrnzMoonshineModel.forward;s[`2C1N-TXT_T_TqTq$8$D $++JjJj "+!6IDKKr>:sd59598<=AEIZ^DHBF$(,0/359{ u001{ !!1!12{ $E$4$45 { !))9)9 : { "%e.?.?(@"AB { "%(;U5CTCT=U(U"VW{  (e.?.?(@A{ 'uU-=-='>?{ D>{ $D>{ 'tn{ !!1!12{  { { rNr>zj The Moonshine Model with a language modeling head. Can be used for automatic speech recognition. ) custom_introceZdZdgZdeffd ZdZdZdZdZ de jfd Z e e dd eej"d eej$d eej$d eej$deeeej"deeeeej"fdeeej"deeej$deedeedeedeej$deej$defdZxZS)!MoonshineForConditionalGenerationzproj_out.weightrcct||t||_t j |j |jd|_|jyr0) rHrIr>rrerfr8r7proj_outr )rJrcrLs rMrIz*MoonshineForConditionalGeneration.__init__sH  #F+  &"4"4f6G6GeT  rNc6|jjSra)r get_encoderrs rMrSz-MoonshineForConditionalGeneration.get_encoderzz%%''rNc6|jjSra)r get_decoderrs rMrVz-MoonshineForConditionalGeneration.get_decoderrTrNc|jSrarQrs rMget_output_embeddingsz7MoonshineForConditionalGeneration.get_output_embeddingss }}rNc||_yrarX)rJnew_embeddingss rMset_output_embeddingsz7MoonshineForConditionalGeneration.set_output_embeddingss & rNrlc6|jjSra)rrrs rMrz6MoonshineForConditionalGeneration.get_input_embeddingsszz..00rNrrr?r@rAr*rBrCrBrrrlabelsc| 9|7|5t| |jj|jj}|j ||||||||| | | |  }|j |j }d}| (|j|| |jj}t|||j|j|j|j|j|j|j  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://arxiv.org/abs/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) rr?rAr@r*rBrCrBrrr)logitsr^r7) lossr`r*rErFr5rGrrH)r&rc pad_token_idr5rrQr loss_functionr7rr*rErFr5rGrrH)rJrrr?r@rAr*rBrCrBrrrr^rr`ras rMrnz)MoonshineForConditionalGeneration.forwards r   (-B-J$6DKK44dkk6X6X%!'+jj )/+#9+"7!5/!5)'1 ' w889  %%VFt{{OeOe%fD#33")"?"?&99$55&-&G&G")"?"?&99  rN) NNNNNNNNNNNNN)rUrVrW_tied_weights_keysr(rIrSrVrYr\rer+rrrrrprrrrr rrrnr\r]s@rMrOrOs ,,(('1bii159598<=AEIZ^DHBF$(,0/359-1{ u001{ !!1!12{ $E$4$45 { !))9)9 : { "%e.?.?(@"AB { "%(;U5CTCT=U(U"VW{  (e.?.?(@A{ 'uU-=-='>?{ D>{ $D>{ 'tn{ !!1!12{ ))*{  { { rNrO)r(r>rrO)Ftypingrrrrrptorch.nnre activationsr cache_utilsr r r configuration_utilsr generationr modeling_attn_mask_utilsrrmodeling_flash_attention_utilsrmodeling_layersrmodeling_outputsrrrrrmodeling_rope_utilsrmodeling_utilsrrprocessing_utilsrutilsrrrglm.modeling_glmrr r!llama.modeling_llamar"r#r$whisper.modeling_whisperr%r& get_loggerrUrr(r+r_rsr{rrrrrr-r>rO__all__r6rNrMrxsQ43 !CC3)gB9:F&>>UUYYG   H %J &J Z "))  "))  q)q)h 1 U-U"U6Up"#"#"#JH /H VK zK \~ \~ B W (@/W  W t rN