turbo-whisper.md

WhisperForConditionalGeneration(
  (model): WhisperModel(
    (encoder): WhisperEncoder(
      (conv1): Conv1d(128, 1280, kernel_size=(3,), stride=(1,), padding=(1,))
      (conv2): Conv1d(1280, 1280, kernel_size=(3,), stride=(2,), padding=(1,))
      (embed_positions): Embedding(1500, 1280)
      (layers): ModuleList(
        (0-31): 32 x WhisperEncoderLayer(
          (self_attn): WhisperSdpaAttention(
            (k_proj): Linear(in_features=1280, out_features=1280, bias=False)
            (v_proj): Linear(in_features=1280, out_features=1280, bias=True)
            (q_proj): Linear(in_features=1280, out_features=1280, bias=True)
            (out_proj): Linear(in_features=1280, out_features=1280, bias=True)
          )
          (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
          (activation_fn): GELUActivation()
          (fc1): Linear(in_features=1280, out_features=5120, bias=True)
          (fc2): Linear(in_features=5120, out_features=1280, bias=True)
          (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
        )
      )
      (layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
    )
    (decoder): WhisperDecoder(
      (embed_tokens): Embedding(51866, 1280, padding_idx=50257)
      (embed_positions): WhisperPositionalEmbedding(448, 1280)
      (layers): ModuleList(
        (0-3): 4 x WhisperDecoderLayer(
          (self_attn): WhisperSdpaAttention(
            (k_proj): HQQLinearTorchWeightOnlynt4()
            (v_proj): HQQLinearTorchWeightOnlynt4()
            (q_proj): HQQLinearTorchWeightOnlynt4()
            (out_proj): HQQLinearTorchWeightOnlynt4()
          )
          (activation_fn): GELUActivation()
          (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
          (encoder_attn): WhisperSdpaAttention(
            (k_proj): HQQLinearTorchWeightOnlynt4()
            (v_proj): HQQLinearTorchWeightOnlynt4()
            (q_proj): HQQLinearTorchWeightOnlynt4()
            (out_proj): HQQLinearTorchWeightOnlynt4()
          )
          (encoder_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
          (fc1): HQQLinearTorchWeightOnlynt4()
          (fc2): HQQLinearTorchWeightOnlynt4()
          (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
        )
      )
      (layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
    )
  )
  (proj_out): Linear(in_features=1280, out_features=51866, bias=False)
)

whisper.md

WhisperForConditionalGeneration(
  (model): WhisperModel(
    (encoder): WhisperEncoder(
      (conv1): Conv1d(128, 1280, kernel_size=(3,), stride=(1,), padding=(1,))
      (conv2): Conv1d(1280, 1280, kernel_size=(3,), stride=(2,), padding=(1,))
      (embed_positions): Embedding(1500, 1280)
      (layers): ModuleList(
        (0-31): 32 x WhisperEncoderLayer(
          (self_attn): WhisperSdpaAttention(
            (k_proj): Linear(in_features=1280, out_features=1280, bias=False)
            (v_proj): Linear(in_features=1280, out_features=1280, bias=True)
            (q_proj): Linear(in_features=1280, out_features=1280, bias=True)
            (out_proj): Linear(in_features=1280, out_features=1280, bias=True)
          )
          (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
          (activation_fn): GELUActivation()
          (fc1): Linear(in_features=1280, out_features=5120, bias=True)
          (fc2): Linear(in_features=5120, out_features=1280, bias=True)
          (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
        )
      )
      (layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
    )
    (decoder): WhisperDecoder(
      (embed_tokens): Embedding(51866, 1280, padding_idx=50256)
      (embed_positions): WhisperPositionalEmbedding(448, 1280)
      (layers): ModuleList(
        (0-31): 32 x WhisperDecoderLayer(
          (self_attn): WhisperSdpaAttention(
            (k_proj): HQQLinearTorchWeightOnlynt4()
            (v_proj): HQQLinearTorchWeightOnlynt4()
            (q_proj): HQQLinearTorchWeightOnlynt4()
            (out_proj): HQQLinearTorchWeightOnlynt4()
          )
          (activation_fn): GELUActivation()
          (self_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
          (encoder_attn): WhisperSdpaAttention(
            (k_proj): HQQLinearTorchWeightOnlynt4()
            (v_proj): HQQLinearTorchWeightOnlynt4()
            (q_proj): HQQLinearTorchWeightOnlynt4()
            (out_proj): HQQLinearTorchWeightOnlynt4()
          )
          (encoder_attn_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
          (fc1): HQQLinearTorchWeightOnlynt4()
          (fc2): HQQLinearTorchWeightOnlynt4()
          (final_layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
        )
      )
      (layer_norm): LayerNorm((1280,), eps=1e-05, elementwise_affine=True)
    )
  )
  (proj_out): Linear(in_features=1280, out_features=51866, bias=False)
)

LGTM!