backup wip

lerobot/common/datasets/factory.py

@@ -125,6 +125,32 @@ def make_offline_buffer(
 
         # TODO(rcadene): remove this and put it in config. Ideally we want to reproduce SOTA results just with mean_std
         normalization_mode = "mean_std" if cfg.env.name == "aloha" else "min_max"
+        
+        # TODO(now): These stats are needed to use their pretrained model for sim_transfer_cube_human.
+        # (Pdb) stats['observation']['state']['mean']
+        # tensor([-0.0071, -0.6293,  1.0351, -0.0517, -0.4642, -0.0754,  0.4751, -0.0373,
+        #         -0.3324,  0.9034, -0.2258, -0.3127, -0.2412,  0.6866])
+        stats['observation', 'state', 'mean'] = torch.tensor([-0.00740268, -0.63187766,  1.0356655 , -0.05027218, -0.46199223,
+            -0.07467502,  0.47467607, -0.03615446, -0.33203387,  0.9038929 ,
+            -0.22060776, -0.31011587, -0.23484458,  0.6842416 ])
+        # (Pdb) stats['observation']['state']['std']
+        # tensor([0.0022, 0.0520, 0.0291, 0.0092, 0.0267, 0.0145, 0.0563, 0.0179, 0.0494,
+        #         0.0326, 0.0476, 0.0535, 0.0956, 0.0513])
+        stats['observation', 'state', 'std'] = torch.tensor([0.01219023, 0.2975381 , 0.16728032, 0.04733803, 0.1486037 ,
+            0.08788499, 0.31752336, 0.1049916 , 0.27933604, 0.18094037,
+            0.26604933, 0.30466506, 0.5298686 , 0.25505227])
+        # (Pdb) stats['action']['mean']
+        # tensor([-0.0075, -0.6346,  1.0353, -0.0465, -0.4686, -0.0738,  0.3723, -0.0396,
+        #         -0.3184,  0.8991, -0.2065, -0.3182, -0.2338,  0.5593])
+        stats['action']['mean'] = torch.tensor([-0.00756444, -0.6281845 ,  1.0312834 , -0.04664314, -0.47211358,
+            -0.074527  ,  0.37389806, -0.03718753, -0.3261143 ,  0.8997205 ,
+            -0.21371077, -0.31840396, -0.23360962,  0.551947])
+        # (Pdb) stats['action']['std']
+        # tensor([0.0023, 0.0514, 0.0290, 0.0086, 0.0263, 0.0143, 0.0593, 0.0185, 0.0510,
+        #         0.0328, 0.0478, 0.0531, 0.0945, 0.0794])
+        stats['action']['std'] = torch.tensor([0.01252818, 0.2957442 , 0.16701928, 0.04584508, 0.14833844,
+            0.08763024, 0.30665937, 0.10600077, 0.27572668, 0.1805853 ,
+            0.26304692, 0.30708534, 0.5305411 , 0.38381037])
         transforms.append(NormalizeTransform(stats, in_keys, mode=normalization_mode))
 
         offline_buffer.set_transform(transforms)

lerobot/common/policies/act/detr_vae.py

@@ -2,6 +2,7 @@ import numpy as np
 import torch
 from torch import nn
 from torch.autograd import Variable
+from transformers import DetrForObjectDetection
 
 from .backbone import build_backbone
 from .transformer import TransformerEncoder, TransformerEncoderLayer, build_transformer
@@ -24,31 +25,57 @@ def get_sinusoid_encoding_table(n_position, d_hid):
     return torch.FloatTensor(sinusoid_table).unsqueeze(0)
 
 
-class DETRVAE(nn.Module):
-    """This is the DETR module that performs object detection"""
+class ActionChunkingTransformer(nn.Module):
+    """
+    Action Chunking Transformer as per Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
+    (https://arxiv.org/abs/2304.13705).
+
+    Note: In this code we use the symbols `vae_encoder`, 'encoder', `decoder`. The meanings are as follows.
+        - The `vae_encoder` is, as per the literature around conditional variational auto-encoders (cVAE), the
+          part of the model that encodes the target data (here, a sequence of actions), and the condition
+          (here, we include the robot joint-space state as an input to the encoder).
+        - The `transformer` is the cVAE's decoder. But since we have an option to train this model without the
+          variational objective (in which case we drop the `vae_encoder` altogether), we don't call it the
+          `vae_decoder`.
+        # TODO(now): remove the following
+        - The `encoder` is actually a component of the cVAE's "decoder". But we refer to it as an "encoder"
+          because, in terms of the transformer with cross-attention that forms the cVAE's decoder, it is the
+          "encoder" part. We drop the `vae_` prefix because we have an option to train this model without the
+          variational objective (in which case we drop the `vae_encoder` altogether), and nothing about this
+          model has anything to do with a VAE).
+        - The `decoder` is a building block of the VAE decoder, and is just the "decoder" part of a
+          transformer with cross-attention. For the same reasoning behind the naming of `encoder`, we make
+          this term agnostic to the option to use a variational objective for training.
+
+    """
 
     def __init__(
-        self, backbones, transformer, encoder, state_dim, action_dim, num_queries, camera_names, vae
+        self, backbones, transformer, vae_encoder, state_dim, action_dim, horizon, camera_names, vae
     ):
         """Initializes the model.
         Parameters:
             backbones: torch module of the backbone to be used. See backbone.py
             transformer: torch module of the transformer architecture. See transformer.py
             state_dim: robot state dimension of the environment
-            num_queries: number of object queries, ie detection slot. This is the maximal number of objects
+            horizon: number of object queries, ie detection slot. This is the maximal number of objects
                          DETR can detect in a single image. For COCO, we recommend 100 queries.
-            aux_loss: True if auxiliary decoding losses (loss at each decoder layer) are to be used.
+
+        Args:
+            state_dim: Robot positional state dimension.
+            action_dim: Action dimension.
+            horizon: The number of actions to generate in one forward pass.
+            vae: Whether to use the variational objective. TODO(now): Give more details.
         """
         super().__init__()
-        self.num_queries = num_queries
         self.camera_names = camera_names
         self.transformer = transformer
-        self.encoder = encoder
+        self.vae_encoder = vae_encoder
         self.vae = vae
         hidden_dim = transformer.d_model
         self.action_head = nn.Linear(hidden_dim, action_dim)
         self.is_pad_head = nn.Linear(hidden_dim, 1)
-        self.query_embed = nn.Embedding(num_queries, hidden_dim)
+        # Positional embedding to be used as input to the latent vae_encoder (if applicable) and for the 
+        self.pos_embed = nn.Embedding(horizon, hidden_dim)
         if backbones is not None:
             self.input_proj = nn.Conv2d(backbones[0].num_channels, hidden_dim, kernel_size=1)
             self.backbones = nn.ModuleList(backbones)
@@ -61,16 +88,16 @@ class DETRVAE(nn.Module):
             self.pos = torch.nn.Embedding(2, hidden_dim)
             self.backbones = None
 
-        # encoder extra parameters
+        # vae_encoder extra parameters
         self.latent_dim = 32  # final size of latent z # TODO tune
         self.cls_embed = nn.Embedding(1, hidden_dim)  # extra cls token embedding
-        self.encoder_action_proj = nn.Linear(14, hidden_dim)  # project action to embedding
-        self.encoder_joint_proj = nn.Linear(14, hidden_dim)  # project qpos to embedding
+        self.vae_encoder_action_proj = nn.Linear(14, hidden_dim)  # project action to embedding
+        self.vae_encoder_joint_proj = nn.Linear(14, hidden_dim)  # project qpos to embedding
         self.latent_proj = nn.Linear(
             hidden_dim, self.latent_dim * 2
         )  # project hidden state to latent std, var
         self.register_buffer(
-            "pos_table", get_sinusoid_encoding_table(1 + 1 + num_queries, hidden_dim)
+            "pos_table", get_sinusoid_encoding_table(1 + 1 + horizon, hidden_dim)
         )  # [CLS], qpos, a_seq
 
         # decoder extra parameters
@@ -91,15 +118,15 @@ class DETRVAE(nn.Module):
         ### Obtain latent z from action sequence
         if self.vae and is_training:
             # project action sequence to embedding dim, and concat with a CLS token
-            action_embed = self.encoder_action_proj(actions)  # (bs, seq, hidden_dim)
-            qpos_embed = self.encoder_joint_proj(qpos)  # (bs, hidden_dim)
+            action_embed = self.vae_encoder_action_proj(actions)  # (bs, seq, hidden_dim)
+            qpos_embed = self.vae_encoder_joint_proj(qpos)  # (bs, hidden_dim)
             qpos_embed = torch.unsqueeze(qpos_embed, axis=1)  # (bs, 1, hidden_dim)
             cls_embed = self.cls_embed.weight  # (1, hidden_dim)
             cls_embed = torch.unsqueeze(cls_embed, axis=0).repeat(bs, 1, 1)  # (bs, 1, hidden_dim)
-            encoder_input = torch.cat(
+            vae_encoder_input = torch.cat(
                 [cls_embed, qpos_embed, action_embed], axis=1
             )  # (bs, seq+1, hidden_dim)
-            encoder_input = encoder_input.permute(1, 0, 2)  # (seq+1, bs, hidden_dim)
+            vae_encoder_input = vae_encoder_input.permute(1, 0, 2)  # (seq+1, bs, hidden_dim)
             # do not mask cls token
             # cls_joint_is_pad = torch.full((bs, 2), False).to(qpos.device)  # False: not a padding
             # is_pad = torch.cat([cls_joint_is_pad, is_pad], axis=1)  # (bs, seq+1)
@@ -107,9 +134,9 @@ class DETRVAE(nn.Module):
             pos_embed = self.pos_table.clone().detach()
             pos_embed = pos_embed.permute(1, 0, 2)  # (seq+1, 1, hidden_dim)
             # query model
-            encoder_output = self.encoder(encoder_input, pos=pos_embed)  # , src_key_padding_mask=is_pad)
-            encoder_output = encoder_output[0]  # take cls output only
-            latent_info = self.latent_proj(encoder_output)
+            vae_encoder_output = self.vae_encoder(vae_encoder_input, pos=pos_embed)  # , src_key_padding_mask=is_pad)
+            vae_encoder_output = vae_encoder_output[0]  # take cls output only
+            latent_info = self.latent_proj(vae_encoder_output)
             mu = latent_info[:, : self.latent_dim]
             logvar = latent_info[:, self.latent_dim :]
             latent_sample = reparametrize(mu, logvar)
@@ -137,7 +164,7 @@ class DETRVAE(nn.Module):
             hs = self.transformer(
                 src,
                 None,
-                self.query_embed.weight,
+                self.pos_embed.weight,
                 pos,
                 latent_input,
                 proprio_input,
@@ -147,7 +174,7 @@ class DETRVAE(nn.Module):
             qpos = self.input_proj_robot_state(qpos)
             env_state = self.input_proj_env_state(env_state)
             transformer_input = torch.cat([qpos, env_state], axis=1)  # seq length = 2
-            hs = self.transformer(transformer_input, None, self.query_embed.weight, self.pos.weight)[0]
+            hs = self.transformer(transformer_input, None, self.pos_embed.weight, self.pos.weight)[0]
         a_hat = self.action_head(hs)
         is_pad_hat = self.is_pad_head(hs)
         return a_hat, is_pad_hat, [mu, logvar]
@@ -165,7 +192,7 @@ def mlp(input_dim, hidden_dim, output_dim, hidden_depth):
     return trunk
 
 
-def build_encoder(args):
+def build_vae_encoder(args):
     d_model = args.hidden_dim  # 256
     dropout = args.dropout  # 0.1
     nhead = args.nheads  # 8
@@ -192,16 +219,16 @@ def build(args):
     backbones.append(backbone)
 
     transformer = build_transformer(args)
+    
+    vae_encoder = build_vae_encoder(args)
 
-    encoder = build_encoder(args)
-
-    model = DETRVAE(
+    model = ActionChunkingTransformer(
         backbones,
         transformer,
-        encoder,
+        vae_encoder,
         state_dim=args.state_dim,
         action_dim=args.action_dim,
-        num_queries=args.num_queries,
+        horizon=args.num_queries,
         camera_names=args.camera_names,
         vae=args.vae,
     )

lerobot/common/policies/act/policy.py

@@ -42,9 +42,28 @@ def kl_divergence(mu, logvar):
 
 
 class ActionChunkingTransformerPolicy(AbstractPolicy):
+    """
+    Action Chunking Transformer as per Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
+    (https://arxiv.org/abs/2304.13705).
+    """
+
     name = "act"
 
     def __init__(self, cfg, device, n_action_steps=1):
+        """
+        Args:
+            vae: Whether to use the variational objective. TODO(now): Give more details.
+            temporal_agg: Whether to do temporal aggregation. For each timestep during rollout, the action
+                returned as an exponential moving average of previously generated actions for that timestep. 
+            n_obs_steps: Number of time steps worth of observation to use as input.
+            horizon: The number of actions to generate in one forward pass.
+            kl_weight: Weight for KL divergence. Defaults to None. Only applicable when using the variational
+                objective.
+            batch_size: Training batch size.
+            grad_clip_norm: Optionally clip the gradients to have this value as the norm at most. Defaults to
+                None meaning gradient clipping is not applied.
+            lr: Learning rate.
+        """
         super().__init__(n_action_steps)
         self.cfg = cfg
         self.n_action_steps = n_action_steps
@@ -57,8 +76,6 @@ class ActionChunkingTransformerPolicy(AbstractPolicy):
     def update(self, replay_buffer, step):
         del step
 
-        start_time = time.time()
-
         self.train()
 
         num_slices = self.cfg.batch_size
@@ -103,11 +120,14 @@ class ActionChunkingTransformerPolicy(AbstractPolicy):
                 "action": action.to(self.device, non_blocking=True),
             }
             return out
+        
+        start_time = time.time()
 
         batch = replay_buffer.sample(batch_size)
         batch = process_batch(batch, self.cfg.horizon, num_slices)
 
         data_s = time.time() - start_time
+        print(data_s)
 
         loss = self.compute_loss(batch)
         loss.backward()
@@ -151,9 +171,6 @@ class ActionChunkingTransformerPolicy(AbstractPolicy):
 
     @torch.no_grad()
     def select_actions(self, observation, step_count):
-        if observation["image"].shape[0] != 1:
-            raise NotImplementedError("Batch size > 1 not handled")
-
         # TODO(rcadene): remove unused step_count
         del step_count
 
@@ -167,7 +184,17 @@ class ActionChunkingTransformerPolicy(AbstractPolicy):
             "image": observation["image", "top"],
             "agent_pos": observation["state"],
         }
-        action = self._forward(qpos=obs_dict["agent_pos"], image=obs_dict["image"])
+        # qpos = obs_dict["agent_pos"]
+        # img = obs_dict["image"]
+        # qpos_ = torch.load('/tmp/qpos.pth')
+        # img_ = torch.load('/tmp/curr_image.pth')
+        # out_ = torch.load('/tmp/out.pth')
+        # import cv2, numpy as np
+        # cv2.imwrite("ours.png", (obs_dict["image"][0, 0].permute(1, 2, 0).cpu().numpy() * 255).astype(np.uint8))
+        # cv2.imwrite("theirs.png", (img_[0, 0].permute(1, 2, 0).cpu().numpy() * 255).astype(np.uint8))
+        # out = self._forward(qpos_, img_)
+        # breakpoint()
+        action = self._forward(qpos=obs_dict["agent_pos"] * 0.182, image=obs_dict["image"])
 
         if self.cfg.temporal_agg:
             # TODO(rcadene): implement temporal aggregation
@@ -197,6 +224,7 @@ class ActionChunkingTransformerPolicy(AbstractPolicy):
             if is_pad is not None:
                 is_pad = is_pad[:, : self.model.num_queries]
 
+            breakpoint()
             a_hat, is_pad_hat, (mu, logvar) = self.model(qpos, image, env_state, actions, is_pad)
 
             all_l1 = F.l1_loss(actions, a_hat, reduction="none")

lerobot/common/policies/factory.py

@@ -1,5 +1,5 @@
 def make_policy(cfg):
-    if cfg.policy.name != "diffusion" and cfg.rollout_batch_size > 1:
+    if cfg.policy.name not in ["diffusion", "act"] and cfg.rollout_batch_size > 1:
         raise NotImplementedError("Only diffusion policy supports rollout_batch_size > 1 for the time being.")
 
     if cfg.policy.name == "tdmpc":

lerobot/configs/policy/act.yaml

@@ -1,6 +1,6 @@
 # @package _global_
 
-offline_steps: 1344000
+offline_steps: 2000
 online_steps: 0
 
 eval_episodes: 1
@@ -24,7 +24,6 @@ policy:
   weight_decay: 1e-4
   grad_clip_norm: 10
   backbone: resnet18
-  num_queries: ${horizon} # chunk_size
   horizon: ${horizon} # chunk_size
   kl_weight: 10
   hidden_dim: 512

lerobot/scripts/train.py

@@ -151,6 +151,7 @@ def train(cfg: dict, out_dir=None, job_name=None):
 
     logging.info("make_policy")
     policy = make_policy(cfg)
+    policy.save("act.pt")
 
     num_learnable_params = sum(p.numel() for p in policy.parameters() if p.requires_grad)
     num_total_params = sum(p.numel() for p in policy.parameters())

poetry.lock

@@ -3248,6 +3248,133 @@ numpy = "*"
 [package.extras]
 all = ["defusedxml", "fsspec", "imagecodecs (>=2023.8.12)", "lxml", "matplotlib", "zarr"]
 
+[[package]]
+name = "tokenizers"
+version = "0.15.2"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "tokenizers-0.15.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:52f6130c9cbf70544287575a985bf44ae1bda2da7e8c24e97716080593638012"},
+    {file = "tokenizers-0.15.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:054c1cc9c6d68f7ffa4e810b3d5131e0ba511b6e4be34157aa08ee54c2f8d9ee"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a9b9b070fdad06e347563b88c278995735292ded1132f8657084989a4c84a6d5"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ea621a7eef4b70e1f7a4e84dd989ae3f0eeb50fc8690254eacc08acb623e82f1"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cf7fd9a5141634fa3aa8d6b7be362e6ae1b4cda60da81388fa533e0b552c98fd"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:44f2a832cd0825295f7179eaf173381dc45230f9227ec4b44378322d900447c9"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8b9ec69247a23747669ec4b0ca10f8e3dfb3545d550258129bd62291aabe8605"},
+    {file = "tokenizers-0.15.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:40b6a4c78da863ff26dbd5ad9a8ecc33d8a8d97b535172601cf00aee9d7ce9ce"},
+    {file = "tokenizers-0.15.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:5ab2a4d21dcf76af60e05af8063138849eb1d6553a0d059f6534357bce8ba364"},
+    {file = "tokenizers-0.15.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a47acfac7e511f6bbfcf2d3fb8c26979c780a91e06fb5b9a43831b2c0153d024"},
+    {file = "tokenizers-0.15.2-cp310-none-win32.whl", hash = "sha256:064ff87bb6acdbd693666de9a4b692add41308a2c0ec0770d6385737117215f2"},
+    {file = "tokenizers-0.15.2-cp310-none-win_amd64.whl", hash = "sha256:3b919afe4df7eb6ac7cafd2bd14fb507d3f408db7a68c43117f579c984a73843"},
+    {file = "tokenizers-0.15.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:89cd1cb93e4b12ff39bb2d626ad77e35209de9309a71e4d3d4672667b4b256e7"},
+    {file = "tokenizers-0.15.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:cfed5c64e5be23d7ee0f0e98081a25c2a46b0b77ce99a4f0605b1ec43dd481fa"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:a907d76dcfda37023ba203ab4ceeb21bc5683436ebefbd895a0841fd52f6f6f2"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20ea60479de6fc7b8ae756b4b097572372d7e4032e2521c1bbf3d90c90a99ff0"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:48e2b9335be2bc0171df9281385c2ed06a15f5cf121c44094338306ab7b33f2c"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:112a1dd436d2cc06e6ffdc0b06d55ac019a35a63afd26475205cb4b1bf0bfbff"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4620cca5c2817177ee8706f860364cc3a8845bc1e291aaf661fb899e5d1c45b0"},
+    {file = "tokenizers-0.15.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ccd73a82751c523b3fc31ff8194702e4af4db21dc20e55b30ecc2079c5d43cb7"},
+    {file = "tokenizers-0.15.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:107089f135b4ae7817affe6264f8c7a5c5b4fd9a90f9439ed495f54fcea56fb4"},
+    {file = "tokenizers-0.15.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0ff110ecc57b7aa4a594396525a3451ad70988e517237fe91c540997c4e50e29"},
+    {file = "tokenizers-0.15.2-cp311-none-win32.whl", hash = "sha256:6d76f00f5c32da36c61f41c58346a4fa7f0a61be02f4301fd30ad59834977cc3"},
+    {file = "tokenizers-0.15.2-cp311-none-win_amd64.whl", hash = "sha256:cc90102ed17271cf0a1262babe5939e0134b3890345d11a19c3145184b706055"},
+    {file = "tokenizers-0.15.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:f86593c18d2e6248e72fb91c77d413a815153b8ea4e31f7cd443bdf28e467670"},
+    {file = "tokenizers-0.15.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0774bccc6608eca23eb9d620196687c8b2360624619623cf4ba9dc9bd53e8b51"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d0222c5b7c9b26c0b4822a82f6a7011de0a9d3060e1da176f66274b70f846b98"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3835738be1de66624fff2f4f6f6684775da4e9c00bde053be7564cbf3545cc66"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:0143e7d9dcd811855c1ce1ab9bf5d96d29bf5e528fd6c7824d0465741e8c10fd"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:db35825f6d54215f6b6009a7ff3eedee0848c99a6271c870d2826fbbedf31a38"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3f5e64b0389a2be47091d8cc53c87859783b837ea1a06edd9d8e04004df55a5c"},
+    {file = "tokenizers-0.15.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9e0480c452217edd35eca56fafe2029fb4d368b7c0475f8dfa3c5c9c400a7456"},
+    {file = "tokenizers-0.15.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a33ab881c8fe70474980577e033d0bc9a27b7ab8272896e500708b212995d834"},
+    {file = "tokenizers-0.15.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a308a607ca9de2c64c1b9ba79ec9a403969715a1b8ba5f998a676826f1a7039d"},
+    {file = "tokenizers-0.15.2-cp312-none-win32.whl", hash = "sha256:b8fcfa81bcb9447df582c5bc96a031e6df4da2a774b8080d4f02c0c16b42be0b"},
+    {file = "tokenizers-0.15.2-cp312-none-win_amd64.whl", hash = "sha256:38d7ab43c6825abfc0b661d95f39c7f8af2449364f01d331f3b51c94dcff7221"},
+    {file = "tokenizers-0.15.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:38bfb0204ff3246ca4d5e726e8cc8403bfc931090151e6eede54d0e0cf162ef0"},
+    {file = "tokenizers-0.15.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:9c861d35e8286a53e06e9e28d030b5a05bcbf5ac9d7229e561e53c352a85b1fc"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:936bf3842db5b2048eaa53dade907b1160f318e7c90c74bfab86f1e47720bdd6"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:620beacc3373277700d0e27718aa8b25f7b383eb8001fba94ee00aeea1459d89"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2735ecbbf37e52db4ea970e539fd2d450d213517b77745114f92867f3fc246eb"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:473c83c5e2359bb81b0b6fde870b41b2764fcdd36d997485e07e72cc3a62264a"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:968fa1fb3c27398b28a4eca1cbd1e19355c4d3a6007f7398d48826bbe3a0f728"},
+    {file = "tokenizers-0.15.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:865c60ae6eaebdde7da66191ee9b7db52e542ed8ee9d2c653b6d190a9351b980"},
+    {file = "tokenizers-0.15.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:7c0d8b52664ab2d4a8d6686eb5effc68b78608a9008f086a122a7b2996befbab"},
+    {file = "tokenizers-0.15.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:f33dfbdec3784093a9aebb3680d1f91336c56d86cc70ddf88708251da1fe9064"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:d44ba80988ff9424e33e0a49445072ac7029d8c0e1601ad25a0ca5f41ed0c1d6"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:dce74266919b892f82b1b86025a613956ea0ea62a4843d4c4237be2c5498ed3a"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0ef06b9707baeb98b316577acb04f4852239d856b93e9ec3a299622f6084e4be"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c73e2e74bbb07910da0d37c326869f34113137b23eadad3fc00856e6b3d9930c"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4eeb12daf02a59e29f578a865f55d87cd103ce62bd8a3a5874f8fdeaa82e336b"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9ba9f6895af58487ca4f54e8a664a322f16c26bbb442effd01087eba391a719e"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ccec77aa7150e38eec6878a493bf8c263ff1fa8a62404e16c6203c64c1f16a26"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3f40604f5042ff210ba82743dda2b6aa3e55aa12df4e9f2378ee01a17e2855e"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:5645938a42d78c4885086767c70923abad047163d809c16da75d6b290cb30bbe"},
+    {file = "tokenizers-0.15.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:05a77cbfebe28a61ab5c3891f9939cc24798b63fa236d84e5f29f3a85a200c00"},
+    {file = "tokenizers-0.15.2-cp37-none-win32.whl", hash = "sha256:361abdc068e8afe9c5b818769a48624687fb6aaed49636ee39bec4e95e1a215b"},
+    {file = "tokenizers-0.15.2-cp37-none-win_amd64.whl", hash = "sha256:7ef789f83eb0f9baeb4d09a86cd639c0a5518528f9992f38b28e819df397eb06"},
+    {file = "tokenizers-0.15.2-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:4fe1f74a902bee74a3b25aff180fbfbf4f8b444ab37c4d496af7afd13a784ed2"},
+    {file = "tokenizers-0.15.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4c4b89038a684f40a6b15d6b09f49650ac64d951ad0f2a3ea9169687bbf2a8ba"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d05a1b06f986d41aed5f2de464c003004b2df8aaf66f2b7628254bcbfb72a438"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:508711a108684111ec8af89d3a9e9e08755247eda27d0ba5e3c50e9da1600f6d"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:daa348f02d15160cb35439098ac96e3a53bacf35885072611cd9e5be7d333daa"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:494fdbe5932d3416de2a85fc2470b797e6f3226c12845cadf054dd906afd0442"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c2d60f5246f4da9373f75ff18d64c69cbf60c3bca597290cea01059c336d2470"},
+    {file = "tokenizers-0.15.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93268e788825f52de4c7bdcb6ebc1fcd4a5442c02e730faa9b6b08f23ead0e24"},
+    {file = "tokenizers-0.15.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6fc7083ab404019fc9acafe78662c192673c1e696bd598d16dc005bd663a5cf9"},
+    {file = "tokenizers-0.15.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:41e39b41e5531d6b2122a77532dbea60e171ef87a3820b5a3888daa847df4153"},
+    {file = "tokenizers-0.15.2-cp38-none-win32.whl", hash = "sha256:06cd0487b1cbfabefb2cc52fbd6b1f8d4c37799bd6c6e1641281adaa6b2504a7"},
+    {file = "tokenizers-0.15.2-cp38-none-win_amd64.whl", hash = "sha256:5179c271aa5de9c71712e31cb5a79e436ecd0d7532a408fa42a8dbfa4bc23fd9"},
+    {file = "tokenizers-0.15.2-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:82f8652a74cc107052328b87ea8b34291c0f55b96d8fb261b3880216a9f9e48e"},
+    {file = "tokenizers-0.15.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:02458bee6f5f3139f1ebbb6d042b283af712c0981f5bc50edf771d6b762d5e4f"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:c9a09cd26cca2e1c349f91aa665309ddb48d71636370749414fbf67bc83c5343"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:158be8ea8554e5ed69acc1ce3fbb23a06060bd4bbb09029431ad6b9a466a7121"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1ddba9a2b0c8c81633eca0bb2e1aa5b3a15362b1277f1ae64176d0f6eba78ab1"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3ef5dd1d39797044642dbe53eb2bc56435308432e9c7907728da74c69ee2adca"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:454c203164e07a860dbeb3b1f4a733be52b0edbb4dd2e5bd75023ffa8b49403a"},
+    {file = "tokenizers-0.15.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0cf6b7f1d4dc59af960e6ffdc4faffe6460bbfa8dce27a58bf75755ffdb2526d"},
+    {file = "tokenizers-0.15.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2ef09bbc16519f6c25d0c7fc0c6a33a6f62923e263c9d7cca4e58b8c61572afb"},
+    {file = "tokenizers-0.15.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c9a2ebdd2ad4ec7a68e7615086e633857c85e2f18025bd05d2a4399e6c5f7169"},
+    {file = "tokenizers-0.15.2-cp39-none-win32.whl", hash = "sha256:918fbb0eab96fe08e72a8c2b5461e9cce95585d82a58688e7f01c2bd546c79d0"},
+    {file = "tokenizers-0.15.2-cp39-none-win_amd64.whl", hash = "sha256:524e60da0135e106b254bd71f0659be9f89d83f006ea9093ce4d1fab498c6d0d"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:6a9b648a58281c4672212fab04e60648fde574877d0139cd4b4f93fe28ca8944"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:7c7d18b733be6bbca8a55084027f7be428c947ddf871c500ee603e375013ffba"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:13ca3611de8d9ddfbc4dc39ef54ab1d2d4aaa114ac8727dfdc6a6ec4be017378"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:237d1bf3361cf2e6463e6c140628e6406766e8b27274f5fcc62c747ae3c6f094"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:67a0fe1e49e60c664915e9fb6b0cb19bac082ab1f309188230e4b2920230edb3"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:4e022fe65e99230b8fd89ebdfea138c24421f91c1a4f4781a8f5016fd5cdfb4d"},
+    {file = "tokenizers-0.15.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:d857be2df69763362ac699f8b251a8cd3fac9d21893de129bc788f8baaef2693"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:708bb3e4283177236309e698da5fcd0879ce8fd37457d7c266d16b550bcbbd18"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64c35e09e9899b72a76e762f9854e8750213f67567787d45f37ce06daf57ca78"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c1257f4394be0d3b00de8c9e840ca5601d0a4a8438361ce9c2b05c7d25f6057b"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:02272fe48280e0293a04245ca5d919b2c94a48b408b55e858feae9618138aeda"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:dc3ad9ebc76eabe8b1d7c04d38be884b8f9d60c0cdc09b0aa4e3bcf746de0388"},
+    {file = "tokenizers-0.15.2-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:32e16bdeffa7c4f46bf2152172ca511808b952701d13e7c18833c0b73cb5c23f"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:fb16ba563d59003028b678d2361a27f7e4ae0ab29c7a80690efa20d829c81fdb"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:2277c36d2d6cdb7876c274547921a42425b6810d38354327dd65a8009acf870c"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:1cf75d32e8d250781940d07f7eece253f2fe9ecdb1dc7ba6e3833fa17b82fcbc"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1b3b31884dc8e9b21508bb76da80ebf7308fdb947a17affce815665d5c4d028"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b10122d8d8e30afb43bb1fe21a3619f62c3e2574bff2699cf8af8b0b6c5dc4a3"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:d88b96ff0fe8e91f6ef01ba50b0d71db5017fa4e3b1d99681cec89a85faf7bf7"},
+    {file = "tokenizers-0.15.2-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:37aaec5a52e959892870a7c47cef80c53797c0db9149d458460f4f31e2fb250e"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e2ea752f2b0fe96eb6e2f3adbbf4d72aaa1272079b0dfa1145507bd6a5d537e6"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:4b19a808d8799fda23504a5cd31d2f58e6f52f140380082b352f877017d6342b"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:64c86e5e068ac8b19204419ed8ca90f9d25db20578f5881e337d203b314f4104"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:de19c4dc503c612847edf833c82e9f73cd79926a384af9d801dcf93f110cea4e"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea09acd2fe3324174063d61ad620dec3bcf042b495515f27f638270a7d466e8b"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:cf27fd43472e07b57cf420eee1e814549203d56de00b5af8659cb99885472f1f"},
+    {file = "tokenizers-0.15.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:7ca22bd897537a0080521445d91a58886c8c04084a6a19e6c78c586e0cfa92a5"},
+    {file = "tokenizers-0.15.2.tar.gz", hash = "sha256:e6e9c6e019dd5484be5beafc775ae6c925f4c69a3487040ed09b45e13df2cb91"},
+]
+
+[package.dependencies]
+huggingface_hub = ">=0.16.4,<1.0"
+
+[package.extras]
+dev = ["tokenizers[testing]"]
+docs = ["setuptools_rust", "sphinx", "sphinx_rtd_theme"]
+testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests"]
+
 [[package]]
 name = "tomli"
 version = "2.0.1"
@@ -3413,6 +3540,74 @@ notebook = ["ipywidgets (>=6)"]
 slack = ["slack-sdk"]
 telegram = ["requests"]
 
+[[package]]
+name = "transformers"
+version = "4.39.3"
+description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "transformers-4.39.3-py3-none-any.whl", hash = "sha256:7838034a12cca3168247f9d2d1dba6724c9de3ae0f73a108258c6b8fc5912601"},
+    {file = "transformers-4.39.3.tar.gz", hash = "sha256:2586e5ff4150f122716fc40f5530e92871befc051848fbe82600969c535b762d"},
+]
+
+[package.dependencies]
+filelock = "*"
+huggingface-hub = ">=0.19.3,<1.0"
+numpy = ">=1.17"
+packaging = ">=20.0"
+pyyaml = ">=5.1"
+regex = "!=2019.12.17"
+requests = "*"
+safetensors = ">=0.4.1"
+tokenizers = ">=0.14,<0.19"
+tqdm = ">=4.27"
+
+[package.extras]
+accelerate = ["accelerate (>=0.21.0)"]
+agents = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch"]
+all = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.14,<0.19)", "torch", "torchaudio", "torchvision"]
+audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+codecarbon = ["codecarbon (==1.2.0)"]
+deepspeed = ["accelerate (>=0.21.0)", "deepspeed (>=0.9.3)"]
+deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.21.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "timeout-decorator"]
+dev = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.14,<0.19)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorboard", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.14,<0.19)", "urllib3 (<2.0.0)"]
+dev-torch = ["GitPython (<3.1.19)", "Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "beautifulsoup4", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "ray[tune] (>=2.7.0)", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorboard", "timeout-decorator", "timm", "tokenizers (>=0.14,<0.19)", "torch", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
+docs = ["Pillow (>=10.0.1,<=15.0)", "accelerate (>=0.21.0)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "hf-doc-builder", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune] (>=2.7.0)", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx", "timm", "tokenizers (>=0.14,<0.19)", "torch", "torchaudio", "torchvision"]
+docs-specific = ["hf-doc-builder"]
+flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)"]
+flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+ftfy = ["ftfy"]
+integrations = ["optuna", "ray[tune] (>=2.7.0)", "sigopt"]
+ja = ["fugashi (>=1.0)", "ipadic (>=1.0.0,<2.0)", "rhoknp (>=1.1.0,<1.3.1)", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)"]
+modelcreation = ["cookiecutter (==1.7.3)"]
+natten = ["natten (>=0.14.6,<0.15.0)"]
+onnx = ["onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "tf2onnx"]
+onnxruntime = ["onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)"]
+optuna = ["optuna"]
+quality = ["GitPython (<3.1.19)", "datasets (!=2.5.0)", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "ruff (==0.1.5)", "urllib3 (<2.0.0)"]
+ray = ["ray[tune] (>=2.7.0)"]
+retrieval = ["datasets (!=2.5.0)", "faiss-cpu"]
+sagemaker = ["sagemaker (>=2.31.0)"]
+sentencepiece = ["protobuf", "sentencepiece (>=0.1.91,!=0.1.92)"]
+serving = ["fastapi", "pydantic", "starlette", "uvicorn"]
+sigopt = ["sigopt"]
+sklearn = ["scikit-learn"]
+speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
+testing = ["GitPython (<3.1.19)", "beautifulsoup4", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "parameterized", "protobuf", "psutil", "pydantic", "pytest (>=7.2.0,<8.0.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (==0.1.5)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "tensorboard", "timeout-decorator"]
+tf = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
+tf-cpu = ["keras-nlp (>=0.3.1)", "onnxconverter-common", "tensorflow-cpu (>=2.6,<2.16)", "tensorflow-text (<2.16)", "tf2onnx"]
+tf-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
+timm = ["timm"]
+tokenizers = ["tokenizers (>=0.14,<0.19)"]
+torch = ["accelerate (>=0.21.0)", "torch"]
+torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
+torch-vision = ["Pillow (>=10.0.1,<=15.0)", "torchvision"]
+torchhub = ["filelock", "huggingface-hub (>=0.19.3,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.14,<0.19)", "torch", "tqdm (>=4.27)"]
+video = ["av (==9.2.0)", "decord (==0.6.0)"]
+vision = ["Pillow (>=10.0.1,<=15.0)"]
+
 [[package]]
 name = "triton"
 version = "2.2.0"
@@ -3589,4 +3784,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "174c7d42f8039eedd2c447a4e6cae5169782cbd94346b5606572a0010194ca05"
+content-hash = "5ebd02dac0322efe1236eb9fec84c471edd0c5373cc8967b1982314164b3bf50"

pyproject.toml

@@ -52,6 +52,7 @@ robomimic = "0.2.0"
 gymnasium-robotics = "^1.2.4"
 gymnasium = "^0.29.1"
 cmake = "^3.29.0.1"
+transformers = "^4.39.3"
 
 
 [tool.poetry.group.dev.dependencies]