Training in progress, step 200

.ipynb_checkpoints/fine-tune-whisper-streaming-checkpoint.ipynb

@@ -19,7 +19,10 @@
   {
    "cell_type": "markdown",
    "id": "afe0d503-ae4e-4aa7-9af4-dbcba52db41e",
-   "metadata": {},
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true,
+    "tags": []
+   },
    "source": [
     "## Introduction"
    ]
@@ -108,10 +111,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 1,
    "id": "065a8cf7-e54f-4ac3-900e-609c80714fca",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/ubuntu/.venv/lib/python3.8/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
    "source": [
     "from datasets import interleave_datasets, load_dataset\n",
     "\n",
@@ -142,7 +154,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 2,
    "id": "a2787582-554f-44ce-9f38-4180a5ed6b44",
    "metadata": {},
    "outputs": [],
@@ -185,7 +197,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 3,
    "id": "77d9f0c5-8607-4642-a8ac-c3ab2e223ea6",
    "metadata": {},
    "outputs": [],
@@ -213,7 +225,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "id": "ab5a13b4-9bd4-4aa0-aef2-b3de9b762988",
    "metadata": {},
    "outputs": [
@@ -233,7 +245,7 @@
        " 'segment': Value(dtype='string', id=None)}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -259,7 +271,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 5,
    "id": "3ab6a724-3d1e-478b-a9e9-d2f85feb6c39",
    "metadata": {},
    "outputs": [],
@@ -279,7 +291,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 6,
    "id": "d041650e-1c48-4439-87b3-5b6f4a514107",
    "metadata": {},
    "outputs": [],
@@ -306,7 +318,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 7,
+   "id": "ce788f4e-1270-424d-b1f3-a10d984ddb31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from fugashi import Tagger\n",
+    "tagger = Tagger('-Owakati')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c858c814-6d32-472e-afe7-2f7273b244ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "FULL2HALF = dict((i + 0xFEE0, i) for i in range(0x21, 0x7F))\n",
+    "FULL2HALF[0x3000] = 0x20"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "id": "c085911c-a10a-41ef-8874-306e0503e9bb",
    "metadata": {},
    "outputs": [],
@@ -326,9 +360,12 @@
     "        transcription = transcription.lower()\n",
     "    if do_remove_punctuation:\n",
     "        transcription = normalizer(transcription).strip()\n",
-    "    \n",
+    "\n",
+    "    input_str = transcription.translate(FULL2HALF)\n",
+    "    input_str = tagger.parse(input_str)\n",
+    "\n",
     "    # encode target text to label ids\n",
-    "    batch[\"labels\"] = processor.tokenizer(transcription).input_ids\n",
+    "    batch[\"labels\"] = processor.tokenizer(input_str).input_ids\n",
     "    return batch"
    ]
   },
@@ -342,7 +379,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684",
    "metadata": {},
    "outputs": [],
@@ -360,7 +397,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "id": "1b145699-acfc-4b1d-93a2-a2ad3d62674c",
    "metadata": {},
    "outputs": [],
@@ -381,7 +418,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 12,
    "id": "01cb25ef-4bb0-4325-9461-f59198acadf6",
    "metadata": {},
    "outputs": [],
@@ -402,7 +439,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 13,
    "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac",
    "metadata": {},
    "outputs": [],
@@ -413,6 +450,63 @@
     ")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "bede1184",
+   "metadata": {
+    "jupyter": {
+     "outputs_hidden": true
+    },
+    "scrolled": true,
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Reading metadata...: 6505it [00:00, 79889.28it/s]\n",
+      "Reading metadata...: 4485it [00:00, 81713.25it/s]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[50258, 50266, 50359, 50363, 6392, 11046, 26923, 2605, 116, 16746]"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "xb = next(iter(vectorized_datasets['train']))\n",
+    "xb['labels'][:10]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "ac1e8d5b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'<|startoftranscript|><|ja|><|transcribe|><|notimestamps|>多から 一 へ と いう の は 、 世界 を 因果 的 に 決定 論 的 に 考える こと で ある 、 過去 から 考える こと で ある 、 機械 的 に 考える こと で ある 。<|endoftext|>'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "processor.tokenizer.decode(xb['labels'])"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "263a5a58-0239-4a25-b0df-c625fc9c5810",
@@ -550,22 +644,7 @@
    "execution_count": 18,
    "id": "b22b4011-f31f-4b57-b684-c52332f92890",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bffdd7b1fed44295954d9eed41a9cfd5",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading builder script:   0%|          | 0.00/4.49k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "import evaluate\n",
     "\n",
@@ -644,36 +723,7 @@
    "execution_count": 20,
    "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "48fee2fd3b2a4a67b3a35666fda4dfe9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/1.97k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "51cdba284e8f44318868fbd013970280",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/967M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from transformers import WhisperForConditionalGeneration\n",
     "\n",
@@ -708,6 +758,34 @@
     "### Define the Training Configuration"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "393c883e-3e50-492c-bd58-f51dbf15ee56",
+   "metadata": {},
+   "source": [
+    "We then define a custom [Callback](https://huggingface.co/docs/transformers/main_classes/callback) that is called by the 🤗 Trainer on the end of each epoch. The Callback reinitialises and reshuffles the streaming dataset at the beginning of each new epoch - this gives different shuffling across our subsets for every epoch."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import TrainerCallback\n",
+    "from transformers.trainer_pt_utils import IterableDatasetShard\n",
+    "from torch.utils.data import IterableDataset\n",
+    "\n",
+    "# trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch\n",
+    "class ShuffleCallback(TrainerCallback):\n",
+    "    def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):\n",
+    "        if isinstance(train_dataloader.dataset, IterableDatasetShard):\n",
+    "            pass  # set_epoch() is handled by the Trainer\n",
+    "        elif isinstance(train_dataloader.dataset, IterableDataset):\n",
+    "            train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "c21af1e9-0188-4134-ac82-defc7bdcc436",
@@ -718,7 +796,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a",
    "metadata": {},
    "outputs": [],
@@ -730,16 +808,16 @@
     "    per_device_train_batch_size=64,\n",
     "    gradient_accumulation_steps=1,  # increase by 2x for every 2x decrease in batch size\n",
     "    learning_rate=1e-5,\n",
-    "    warmup_steps=200,\n",
+    "    warmup_steps=500,\n",
     "    max_steps=1000,\n",
     "    gradient_checkpointing=True,\n",
     "    fp16=True,\n",
     "    evaluation_strategy=\"steps\",\n",
-    "    per_device_eval_batch_size=8,\n",
+    "    per_device_eval_batch_size=32,\n",
     "    predict_with_generate=True,\n",
     "    generation_max_length=225,\n",
     "    save_steps=200,\n",
-    "    eval_steps=200,\n",
+    "    eval_steps=100,\n",
     "    logging_steps=25,\n",
     "    report_to=[\"tensorboard\"],\n",
     "    load_best_model_at_end=True,\n",
@@ -758,34 +836,6 @@
     "set `push_to_hub=False`."
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "393c883e-3e50-492c-bd58-f51dbf15ee56",
-   "metadata": {},
-   "source": [
-    "We then define a custom [Callback](https://huggingface.co/docs/transformers/main_classes/callback) that is called by the 🤗 Trainer on the end of each epoch. The Callback reinitialises and reshuffles the streaming dataset at the beginning of each new epoch - this gives different shuffling across our subsets for every epoch."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from transformers import TrainerCallback\n",
-    "from transformers.trainer_pt_utils import IterableDatasetShard\n",
-    "from torch.utils.data import IterableDataset\n",
-    "\n",
-    "# trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch\n",
-    "class ShuffleCallback(TrainerCallback):\n",
-    "    def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):\n",
-    "        if isinstance(train_dataloader.dataset, IterableDatasetShard):\n",
-    "            pass  # set_epoch() is handled by the Trainer\n",
-    "        elif isinstance(train_dataloader.dataset, IterableDataset):\n",
-    "            train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "bac29114-d226-4f54-97cf-8718c9f94e1e",
@@ -884,7 +934,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
-   "metadata": {},
+   "metadata": {
+    "scrolled": false
+   },
    "outputs": [
     {
      "name": "stderr",
@@ -900,8 +952,8 @@
       "  Gradient Accumulation steps = 1\n",
       "  Total optimization steps = 1000\n",
       "  Number of trainable parameters = 241734912\n",
-      "Reading metadata...: 6505it [00:00, 31331.40it/s]\n",
-      "Reading metadata...: 4485it [00:00, 41376.86it/s]\n",
+      "Reading metadata...: 6505it [00:00, 33561.53it/s]\n",
+      "Reading metadata...: 4485it [00:00, 24503.43it/s]\n",
       "The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n"
      ]
     },
@@ -911,8 +963,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='201' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [ 201/1000 22:31 < 1:30:27, 0.15 it/s, Epoch 1.06/9223372036854775807]\n",
+       "      <progress value='101' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [ 101/1000 11:45 < 1:46:47, 0.14 it/s, Epoch 0.10/9223372036854775807]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -937,12 +989,10 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Reading metadata...: 6505it [00:00, 64162.65it/s]\n",
-      "Reading metadata...: 4485it [00:00, 27834.06it/s]\n",
       "***** Running Evaluation *****\n",
       "  Num examples: Unknown\n",
-      "  Batch size = 8\n",
-      "Reading metadata...: 4604it [00:00, 27155.92it/s]\n",
+      "  Batch size = 32\n",
+      "Reading metadata...: 4604it [00:00, 79017.99it/s]\n",
       "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n"
      ]
     }
@@ -973,7 +1023,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": null,
    "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
    "metadata": {},
    "outputs": [],
@@ -999,275 +1049,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": null,
    "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Saving model checkpoint to ./\n",
-      "Configuration saved in ./config.json\n",
-      "Model weights saved in ./pytorch_model.bin\n",
-      "Feature extractor saved in ./preprocessor_config.json\n",
-      "tokenizer config file saved in ./tokenizer_config.json\n",
-      "Special tokens file saved in ./special_tokens_map.json\n",
-      "added tokens file saved in ./added_tokens.json\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "695c170663c94560a567be198b7181ff",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Upload file runs/Dec10_16-23-25_129-213-27-84/1670689420.7830398/events.out.tfevents.1670689420.129-213-27-84.…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2318836d6dd3405fabafca4370232e34",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Upload file training_args.bin: 100%|##########| 3.50k/3.50k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9b673eb134984bdda227d23929b66479",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Upload file runs/Dec10_16-23-25_129-213-27-84/events.out.tfevents.1670689420.129-213-27-84.69598.2: 100%|#####…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "remote: Scanning LFS files for validity, may be slow...        \n",
-      "remote: LFS file scan complete.        \n",
-      "To https://huggingface.co/kimbochen/whisper-small-jp\n",
-      "   3a44fa5..05da956  main -> main\n",
-      "\n",
-      "To https://huggingface.co/kimbochen/whisper-small-jp\n",
-      "   05da956..30906c5  main -> main\n",
-      "\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'https://huggingface.co/kimbochen/whisper-small-jp/commit/05da956fdc97e7c01112f45c20e56c8f6a127502'"
-      ]
-     },
-     "execution_count": 31,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "trainer.push_to_hub(**kwargs)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "4df1603c-ef35-40f1-ae57-3214441073c8",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "PyTorch: setting up devices\n"
-     ]
-    }
-   ],
-   "source": [
-    "training_args = Seq2SeqTrainingArguments(\n",
-    "    output_dir=\"./\",\n",
-    "    per_device_train_batch_size=64,\n",
-    "    gradient_accumulation_steps=1,  # increase by 2x for every 2x decrease in batch size\n",
-    "    learning_rate=1e-5,\n",
-    "    max_steps=1000,\n",
-    "    num_train_epochs=-1,\n",
-    "    gradient_checkpointing=True,\n",
-    "    fp16=True,\n",
-    "    evaluation_strategy=\"steps\",\n",
-    "    per_device_eval_batch_size=8,\n",
-    "    predict_with_generate=True,\n",
-    "    generation_max_length=225,\n",
-    "    save_steps=1000,\n",
-    "    eval_steps=1000,\n",
-    "    logging_steps=25,\n",
-    "    report_to=[\"tensorboard\"],\n",
-    "    load_best_model_at_end=True,\n",
-    "    metric_for_best_model=\"wer\",\n",
-    "    greater_is_better=False,\n",
-    "    push_to_hub=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "afc2b554-7171-48c7-95aa-b7e61b70ab20",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/ubuntu/whisper-small-jp/./ is already a clone of https://huggingface.co/kimbochen/whisper-small-jp. Make sure you pull the latest changes with `repo.git_pull()`.\n",
-      "max_steps is given, it will override any value given in num_train_epochs\n",
-      "Using cuda_amp half precision backend\n"
-     ]
-    }
-   ],
-   "source": [
-    "trainer = Seq2SeqTrainer(\n",
-    "    args=training_args,\n",
-    "    model=model,\n",
-    "    train_dataset=vectorized_datasets[\"train\"],\n",
-    "    eval_dataset=vectorized_datasets[\"test\"],\n",
-    "    data_collator=data_collator,\n",
-    "    compute_metrics=compute_metrics,\n",
-    "    tokenizer=processor,\n",
-    "    callbacks=[ShuffleCallback()],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "id": "b029a1d8-24de-46e7-b067-0f900b1db342",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Loading model from checkpoint-4000.\n",
-      "/home/ubuntu/.venv/lib/python3.8/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
-      "  warnings.warn(\n",
-      "***** Running training *****\n",
-      "  Num examples = 64000\n",
-      "  Num Epochs = 9223372036854775807\n",
-      "  Instantaneous batch size per device = 64\n",
-      "  Total train batch size (w. parallel, distributed & accumulation) = 64\n",
-      "  Gradient Accumulation steps = 1\n",
-      "  Total optimization steps = 1000\n",
-      "  Number of trainable parameters = 241734912\n",
-      "  Continuing training from checkpoint, will skip to saved global_step\n",
-      "  Continuing training from epoch 4\n",
-      "  Continuing training from global step 4000\n",
-      "  Will skip the first 4 epochs then the first 0 batches in the first epoch. If this takes a lot of time, you can add the `--ignore_data_skip` flag to your launch command, but you will resume the training on data already seen by your model.\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "01337298313740d98d3cc75b6d5e3ff7",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "0it [00:00, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Reading metadata...: 0it [00:00, ?it/s]\u001b[A\n",
-      "Reading metadata...: 6505it [00:00, 34246.80it/s]\n",
-      "The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n",
-      "\n",
-      "Reading metadata...: 6505it [00:00, 84823.64it/s]\n",
-      "\n",
-      "Reading metadata...: 6505it [00:00, 88617.62it/s]\n",
-      "\n",
-      "Reading metadata...: 6505it [00:00, 90289.78it/s]\n",
-      "\n",
-      "Reading metadata...: 6505it [00:00, 91816.92it/s]\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='4001' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1000/1000 00:00, Epoch 4/9223372036854775807]\n",
-       "    </div>\n",
-       "    <table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       " <tr style=\"text-align: left;\">\n",
-       "      <th>Step</th>\n",
-       "      <th>Training Loss</th>\n",
-       "      <th>Validation Loss</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "  </tbody>\n",
-       "</table><p>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "Training completed. Do not forget to share your model on huggingface.co/models =)\n",
-      "\n",
-      "\n",
-      "Loading best model from ./checkpoint-4000 (score: 88.31039863810469).\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "TrainOutput(global_step=4001, training_loss=8.343380785802548e-08, metrics={'train_runtime': 169.0541, 'train_samples_per_second': 378.577, 'train_steps_per_second': 5.915, 'total_flos': 7.363747084345344e+19, 'train_loss': 8.343380785802548e-08, 'epoch': 4.0})"
-      ]
-     },
-     "execution_count": 30,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "trainer.train(\"checkpoint-4000\")"
-   ]
   }
  ],
  "metadata": {

config.json

@@ -34,7 +34,6 @@
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "suppress_tokens": [],
   "torch_dtype": "float32",
   "transformers_version": "4.26.0.dev0",
   "use_cache": false,

fine-tune-whisper-streaming.ipynb

@@ -19,7 +19,10 @@
   {
    "cell_type": "markdown",
    "id": "afe0d503-ae4e-4aa7-9af4-dbcba52db41e",
-   "metadata": {},
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true,
+    "tags": []
+   },
    "source": [
     "## Introduction"
    ]
@@ -108,10 +111,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 1,
    "id": "065a8cf7-e54f-4ac3-900e-609c80714fca",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/ubuntu/.venv/lib/python3.8/site-packages/tqdm/auto.py:22: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
    "source": [
     "from datasets import interleave_datasets, load_dataset\n",
     "\n",
@@ -142,7 +154,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 2,
    "id": "a2787582-554f-44ce-9f38-4180a5ed6b44",
    "metadata": {},
    "outputs": [],
@@ -185,7 +197,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 3,
    "id": "77d9f0c5-8607-4642-a8ac-c3ab2e223ea6",
    "metadata": {},
    "outputs": [],
@@ -213,7 +225,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "id": "ab5a13b4-9bd4-4aa0-aef2-b3de9b762988",
    "metadata": {},
    "outputs": [
@@ -233,7 +245,7 @@
        " 'segment': Value(dtype='string', id=None)}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -259,7 +271,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 5,
    "id": "3ab6a724-3d1e-478b-a9e9-d2f85feb6c39",
    "metadata": {},
    "outputs": [],
@@ -279,7 +291,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 6,
    "id": "d041650e-1c48-4439-87b3-5b6f4a514107",
    "metadata": {},
    "outputs": [],
@@ -306,7 +318,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 7,
+   "id": "ce788f4e-1270-424d-b1f3-a10d984ddb31",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from fugashi import Tagger\n",
+    "tagger = Tagger('-Owakati')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c858c814-6d32-472e-afe7-2f7273b244ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "FULL2HALF = dict((i + 0xFEE0, i) for i in range(0x21, 0x7F))\n",
+    "FULL2HALF[0x3000] = 0x20"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "id": "c085911c-a10a-41ef-8874-306e0503e9bb",
    "metadata": {},
    "outputs": [],
@@ -326,10 +360,12 @@
     "        transcription = transcription.lower()\n",
     "    if do_remove_punctuation:\n",
     "        transcription = normalizer(transcription).strip()\n",
-    "    \n",
+    "\n",
+    "    input_str = transcription.translate(FULL2HALF)\n",
+    "    input_str = tagger.parse(input_str)\n",
+    "\n",
     "    # encode target text to label ids\n",
-    "#     batch[\"labels\"] = processor.tokenizer(transcription).input_ids\n",
-    "    batch['labels'] = transcription\n",
+    "    batch[\"labels\"] = processor.tokenizer(input_str).input_ids\n",
     "    return batch"
    ]
   },
@@ -343,7 +379,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 10,
    "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684",
    "metadata": {},
    "outputs": [],
@@ -361,7 +397,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 11,
    "id": "1b145699-acfc-4b1d-93a2-a2ad3d62674c",
    "metadata": {},
    "outputs": [],
@@ -382,7 +418,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 12,
    "id": "01cb25ef-4bb0-4325-9461-f59198acadf6",
    "metadata": {},
    "outputs": [],
@@ -403,7 +439,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 13,
    "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac",
    "metadata": {},
    "outputs": [],
@@ -416,250 +452,59 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 14,
    "id": "bede1184",
-   "metadata": {},
+   "metadata": {
+    "jupyter": {
+     "outputs_hidden": true
+    },
+    "scrolled": true,
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Reading metadata...: 6505it [00:00, 35406.66it/s]\n",
-      "Reading metadata...: 4485it [00:00, 19930.24it/s]\n"
+      "Reading metadata...: 6505it [00:00, 79889.28it/s]\n",
+      "Reading metadata...: 4485it [00:00, 81713.25it/s]\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "'多から一へというのは、世界を因果的に決定論的に考えることである、過去から考えることである、機械的に考えること��ある。'"
+       "[50258, 50266, 50359, 50363, 6392, 11046, 26923, 2605, 116, 16746]"
       ]
      },
-     "execution_count": 49,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "xb = next(iter(vectorized_datasets['train']))\n",
-    "xb['labels']"
+    "xb['labels'][:10]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 15,
    "id": "ac1e8d5b",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<|startoftranscript|>\n",
-      "<|ja|>\n",
-      "<|transcribe|>\n",
-      "<|notimestamps|>\n",
-      "多\n",
-      "から\n",
-      "一\n",
-      "へ\n",
-      "という\n",
-      "のは\n",
-      "、\n",
-      "世界\n",
-      "を\n",
-      "因\n",
-      "果\n",
-      "的\n",
-      "に\n",
-      "決\n",
-      "定\n",
-      "論\n",
-      "的\n",
-      "に\n",
-      "考\n",
-      "える\n",
-      "こと\n",
-      "で\n",
-      "ある\n",
-      "、\n",
-      "過去\n",
-      "から\n",
-      "考\n",
-      "える\n",
-      "こと\n",
-      "で\n",
-      "ある\n",
-      "、\n",
-      "機\n",
-      "�\n",
-      "�\n",
-      "的\n",
-      "に\n",
-      "考\n",
-      "える\n",
-      "こと\n",
-      "で\n",
-      "ある\n",
-      "。\n",
-      "<|endoftext|>\n"
-     ]
-    }
-   ],
-   "source": [
-    "idxs = processor.tokenizer(xb['labels']).input_ids\n",
-    "for idx in idxs:\n",
-    "    print(processor.tokenizer.decode(idx))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 60,
-   "id": "d33cefc4",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[多から,\n",
-       " 一,\n",
-       " へ,\n",
-       " と,\n",
-       " いう,\n",
-       " の,\n",
-       " は,\n",
-       " 、,\n",
-       " 世界,\n",
-       " を,\n",
-       " 因果,\n",
-       " 的,\n",
-       " に,\n",
-       " 決定,\n",
-       " 論,\n",
-       " 的,\n",
-       " に,\n",
-       " 考える,\n",
-       " こと,\n",
-       " で,\n",
-       " ある,\n",
-       " 、,\n",
-       " 過去,\n",
-       " から,\n",
-       " 考える,\n",
-       " こと,\n",
-       " で,\n",
-       " ある,\n",
-       " 、,\n",
-       " 機械,\n",
-       " 的,\n",
-       " に,\n",
-       " 考える,\n",
-       " こと,\n",
-       " で,\n",
-       " ある,\n",
-       " 。]"
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tagger(xb['labels'])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "id": "2cbb82ef",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Help on method decode in module transformers.tokenization_utils_base:\n",
-      "\n",
-      "decode(token_ids: Union[int, List[int], ForwardRef('np.ndarray'), ForwardRef('torch.Tensor'), ForwardRef('tf.Tensor')], skip_special_tokens: bool = False, clean_up_tokenization_spaces: bool = True, **kwargs) -> str method of transformers.models.whisper.tokenization_whisper.WhisperTokenizer instance\n",
-      "    Converts a sequence of ids in a string, using the tokenizer and vocabulary with options to remove special\n",
-      "    tokens and clean up tokenization spaces.\n",
-      "    \n",
-      "    Similar to doing `self.convert_tokens_to_string(self.convert_ids_to_tokens(token_ids))`.\n",
-      "    \n",
-      "    Args:\n",
-      "        token_ids (`Union[int, List[int], np.ndarray, torch.Tensor, tf.Tensor]`):\n",
-      "            List of tokenized input ids. Can be obtained using the `__call__` method.\n",
-      "        skip_special_tokens (`bool`, *optional*, defaults to `False`):\n",
-      "            Whether or not to remove special tokens in the decoding.\n",
-      "        clean_up_tokenization_spaces (`bool`, *optional*, defaults to `True`):\n",
-      "            Whether or not to clean up the tokenization spaces.\n",
-      "        kwargs (additional keyword arguments, *optional*):\n",
-      "            Will be passed to the underlying model specific decode method.\n",
-      "    \n",
-      "    Returns:\n",
-      "        `str`: The decoded sentence.\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "help(processor.tokenizer.decode)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 41,
-   "id": "b4b9bbfc",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'麩 菓子 は 、 麩 を 主材 料 と し た 日本 の 菓子 。'"
+       "'<|startoftranscript|><|ja|><|transcribe|><|notimestamps|>多から 一 へ と いう の は 、 世界 を 因果 的 に 決定 論 的 に 考える こと で ある 、 過去 から 考える こと で ある 、 機械 的 に 考える こと で ある 。<|endoftext|>'"
       ]
      },
-     "execution_count": 41,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from fugashi import Tagger\n",
-    "\n",
-    "tagger = Tagger('-Owakati')\n",
-    "text = \"麩菓子は、麩を主材料とした日本の菓子。\"\n",
-    "tagger.parse(text)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 43,
-   "id": "833ca62d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[麩, 菓子, は, 、, 麩, を, 主材, 料, と, し, た, 日本, の, 菓子, 。]"
-      ]
-     },
-     "execution_count": 43,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tagger(text)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7b7854d6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "raw_datasets['']"
+    "processor.tokenizer.decode(xb['labels'])"
    ]
   },
   {
@@ -799,22 +644,7 @@
    "execution_count": 18,
    "id": "b22b4011-f31f-4b57-b684-c52332f92890",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bffdd7b1fed44295954d9eed41a9cfd5",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading builder script:   0%|          | 0.00/4.49k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "import evaluate\n",
     "\n",
@@ -893,36 +723,7 @@
    "execution_count": 20,
    "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "48fee2fd3b2a4a67b3a35666fda4dfe9",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/1.97k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "51cdba284e8f44318868fbd013970280",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/967M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from transformers import WhisperForConditionalGeneration\n",
     "\n",
@@ -957,6 +758,34 @@
     "### Define the Training Configuration"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "393c883e-3e50-492c-bd58-f51dbf15ee56",
+   "metadata": {},
+   "source": [
+    "We then define a custom [Callback](https://huggingface.co/docs/transformers/main_classes/callback) that is called by the 🤗 Trainer on the end of each epoch. The Callback reinitialises and reshuffles the streaming dataset at the beginning of each new epoch - this gives different shuffling across our subsets for every epoch."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import TrainerCallback\n",
+    "from transformers.trainer_pt_utils import IterableDatasetShard\n",
+    "from torch.utils.data import IterableDataset\n",
+    "\n",
+    "# trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch\n",
+    "class ShuffleCallback(TrainerCallback):\n",
+    "    def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):\n",
+    "        if isinstance(train_dataloader.dataset, IterableDatasetShard):\n",
+    "            pass  # set_epoch() is handled by the Trainer\n",
+    "        elif isinstance(train_dataloader.dataset, IterableDataset):\n",
+    "            train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "c21af1e9-0188-4134-ac82-defc7bdcc436",
@@ -967,7 +796,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a",
    "metadata": {},
    "outputs": [],
@@ -979,16 +808,16 @@
     "    per_device_train_batch_size=64,\n",
     "    gradient_accumulation_steps=1,  # increase by 2x for every 2x decrease in batch size\n",
     "    learning_rate=1e-5,\n",
-    "    warmup_steps=200,\n",
+    "    warmup_steps=500,\n",
     "    max_steps=1000,\n",
     "    gradient_checkpointing=True,\n",
     "    fp16=True,\n",
     "    evaluation_strategy=\"steps\",\n",
-    "    per_device_eval_batch_size=8,\n",
+    "    per_device_eval_batch_size=32,\n",
     "    predict_with_generate=True,\n",
     "    generation_max_length=225,\n",
     "    save_steps=200,\n",
-    "    eval_steps=200,\n",
+    "    eval_steps=100,\n",
     "    logging_steps=25,\n",
     "    report_to=[\"tensorboard\"],\n",
     "    load_best_model_at_end=True,\n",
@@ -1007,34 +836,6 @@
     "set `push_to_hub=False`."
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "393c883e-3e50-492c-bd58-f51dbf15ee56",
-   "metadata": {},
-   "source": [
-    "We then define a custom [Callback](https://huggingface.co/docs/transformers/main_classes/callback) that is called by the 🤗 Trainer on the end of each epoch. The Callback reinitialises and reshuffles the streaming dataset at the beginning of each new epoch - this gives different shuffling across our subsets for every epoch."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from transformers import TrainerCallback\n",
-    "from transformers.trainer_pt_utils import IterableDatasetShard\n",
-    "from torch.utils.data import IterableDataset\n",
-    "\n",
-    "# trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch\n",
-    "class ShuffleCallback(TrainerCallback):\n",
-    "    def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):\n",
-    "        if isinstance(train_dataloader.dataset, IterableDatasetShard):\n",
-    "            pass  # set_epoch() is handled by the Trainer\n",
-    "        elif isinstance(train_dataloader.dataset, IterableDataset):\n",
-    "            train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "bac29114-d226-4f54-97cf-8718c9f94e1e",
@@ -1131,10 +932,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": null,
    "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
    "metadata": {
-    "scrolled": true
+    "scrolled": false
    },
    "outputs": [
     {
@@ -1151,8 +952,8 @@
       "  Gradient Accumulation steps = 1\n",
       "  Total optimization steps = 1000\n",
       "  Number of trainable parameters = 241734912\n",
-      "Reading metadata...: 6505it [00:00, 31331.40it/s]\n",
-      "Reading metadata...: 4485it [00:00, 41376.86it/s]\n",
+      "Reading metadata...: 6505it [00:00, 33561.53it/s]\n",
+      "Reading metadata...: 4485it [00:00, 24503.43it/s]\n",
       "The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n"
      ]
     },
@@ -1162,8 +963,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='1001' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1000/1000 3:35:08, Epoch 7.01/9223372036854775807]\n",
+       "      <progress value='101' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [ 101/1000 11:45 < 1:46:47, 0.14 it/s, Epoch 0.10/9223372036854775807]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -1171,34 +972,9 @@
        "      <th>Step</th>\n",
        "      <th>Training Loss</th>\n",
        "      <th>Validation Loss</th>\n",
-       "      <th>Wer</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
-       "    <tr>\n",
-       "      <td>200</td>\n",
-       "      <td>0.220800</td>\n",
-       "      <td>0.278119</td>\n",
-       "      <td>81.117889</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>400</td>\n",
-       "      <td>0.136700</td>\n",
-       "      <td>0.269168</td>\n",
-       "      <td>73.102568</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>600</td>\n",
-       "      <td>0.033800</td>\n",
-       "      <td>0.278346</td>\n",
-       "      <td>70.960420</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <td>800</td>\n",
-       "      <td>0.026300</td>\n",
-       "      <td>0.298785</td>\n",
-       "      <td>74.734005</td>\n",
-       "    </tr>\n",
        "  </tbody>\n",
        "</table><p>"
       ],
@@ -1213,117 +989,12 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Reading metadata...: 6505it [00:00, 64162.65it/s]\n",
-      "Reading metadata...: 4485it [00:00, 27834.06it/s]\n",
       "***** Running Evaluation *****\n",
       "  Num examples: Unknown\n",
-      "  Batch size = 8\n",
-      "Reading metadata...: 4604it [00:00, 27155.92it/s]\n",
-      "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n",
-      "Saving model checkpoint to ./checkpoint-200\n",
-      "Configuration saved in ./checkpoint-200/config.json\n",
-      "Model weights saved in ./checkpoint-200/pytorch_model.bin\n",
-      "Feature extractor saved in ./checkpoint-200/preprocessor_config.json\n",
-      "tokenizer config file saved in ./checkpoint-200/tokenizer_config.json\n",
-      "Special tokens file saved in ./checkpoint-200/special_tokens_map.json\n",
-      "added tokens file saved in ./checkpoint-200/added_tokens.json\n",
-      "Feature extractor saved in ./preprocessor_config.json\n",
-      "tokenizer config file saved in ./tokenizer_config.json\n",
-      "Special tokens file saved in ./special_tokens_map.json\n",
-      "added tokens file saved in ./added_tokens.json\n",
-      "Reading metadata...: 6505it [00:00, 44457.32it/s]\n",
-      "Reading metadata...: 4485it [00:00, 29197.09it/s]\n",
-      "***** Running Evaluation *****\n",
-      "  Num examples: Unknown\n",
-      "  Batch size = 8\n",
-      "Reading metadata...: 4604it [00:00, 34447.62it/s]\n",
-      "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n",
-      "Saving model checkpoint to ./checkpoint-400\n",
-      "Configuration saved in ./checkpoint-400/config.json\n",
-      "Model weights saved in ./checkpoint-400/pytorch_model.bin\n",
-      "Feature extractor saved in ./checkpoint-400/preprocessor_config.json\n",
-      "tokenizer config file saved in ./checkpoint-400/tokenizer_config.json\n",
-      "Special tokens file saved in ./checkpoint-400/special_tokens_map.json\n",
-      "added tokens file saved in ./checkpoint-400/added_tokens.json\n",
-      "Feature extractor saved in ./preprocessor_config.json\n",
-      "tokenizer config file saved in ./tokenizer_config.json\n",
-      "Special tokens file saved in ./special_tokens_map.json\n",
-      "added tokens file saved in ./added_tokens.json\n",
-      "Reading metadata...: 6505it [00:00, 33208.71it/s]\n",
-      "Reading metadata...: 4485it [00:00, 23213.70it/s]\n",
-      "Reading metadata...: 6505it [00:00, 25768.67it/s]\n",
-      "Reading metadata...: 4485it [00:00, 27756.07it/s]\n",
-      "***** Running Evaluation *****\n",
-      "  Num examples: Unknown\n",
-      "  Batch size = 8\n",
-      "Reading metadata...: 4604it [00:00, 28855.43it/s]\n",
-      "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n",
-      "Saving model checkpoint to ./checkpoint-600\n",
-      "Configuration saved in ./checkpoint-600/config.json\n",
-      "Model weights saved in ./checkpoint-600/pytorch_model.bin\n",
-      "Feature extractor saved in ./checkpoint-600/preprocessor_config.json\n",
-      "tokenizer config file saved in ./checkpoint-600/tokenizer_config.json\n",
-      "Special tokens file saved in ./checkpoint-600/special_tokens_map.json\n",
-      "added tokens file saved in ./checkpoint-600/added_tokens.json\n",
-      "Feature extractor saved in ./preprocessor_config.json\n",
-      "tokenizer config file saved in ./tokenizer_config.json\n",
-      "Special tokens file saved in ./special_tokens_map.json\n",
-      "added tokens file saved in ./added_tokens.json\n",
-      "Reading metadata...: 6505it [00:00, 86030.70it/s]\n",
-      "Reading metadata...: 4485it [00:00, 68522.65it/s]\n",
-      "***** Running Evaluation *****\n",
-      "  Num examples: Unknown\n",
-      "  Batch size = 8\n",
-      "Reading metadata...: 4604it [00:00, 30988.60it/s]\n",
-      "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n",
-      "Saving model checkpoint to ./checkpoint-800\n",
-      "Configuration saved in ./checkpoint-800/config.json\n",
-      "Model weights saved in ./checkpoint-800/pytorch_model.bin\n",
-      "Feature extractor saved in ./checkpoint-800/preprocessor_config.json\n",
-      "tokenizer config file saved in ./checkpoint-800/tokenizer_config.json\n",
-      "Special tokens file saved in ./checkpoint-800/special_tokens_map.json\n",
-      "added tokens file saved in ./checkpoint-800/added_tokens.json\n",
-      "Feature extractor saved in ./preprocessor_config.json\n",
-      "tokenizer config file saved in ./tokenizer_config.json\n",
-      "Special tokens file saved in ./special_tokens_map.json\n",
-      "added tokens file saved in ./added_tokens.json\n",
-      "Reading metadata...: 6505it [00:00, 36357.17it/s]\n",
-      "Reading metadata...: 4485it [00:00, 30574.75it/s]\n",
-      "Got disconnected from remote data host. Retrying in 5sec [1/20]\n",
-      "Got disconnected from remote data host. Retrying in 5sec [2/20]\n",
-      "Reading metadata...: 6505it [00:00, 31147.16it/s]\n",
-      "Reading metadata...: 4485it [00:00, 22808.34it/s]\n",
-      "***** Running Evaluation *****\n",
-      "  Num examples: Unknown\n",
-      "  Batch size = 8\n",
-      "Reading metadata...: 4604it [00:00, 28132.71it/s]\n",
+      "  Batch size = 32\n",
+      "Reading metadata...: 4604it [00:00, 79017.99it/s]\n",
       "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n"
      ]
-    },
-    {
-     "ename": "KeyboardInterrupt",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[26], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/trainer.py:1535\u001b[0m, in \u001b[0;36mTrainer.train\u001b[0;34m(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)\u001b[0m\n\u001b[1;32m   1530\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel_wrapped \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\n\u001b[1;32m   1532\u001b[0m inner_training_loop \u001b[38;5;241m=\u001b[39m find_executable_batch_size(\n\u001b[1;32m   1533\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_inner_training_loop, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_train_batch_size, args\u001b[38;5;241m.\u001b[39mauto_find_batch_size\n\u001b[1;32m   1534\u001b[0m )\n\u001b[0;32m-> 1535\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43minner_training_loop\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1536\u001b[0m \u001b[43m    \u001b[49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1537\u001b[0m \u001b[43m    \u001b[49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_from_checkpoint\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1538\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtrial\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtrial\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1539\u001b[0m \u001b[43m    \u001b[49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1540\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/trainer.py:1860\u001b[0m, in \u001b[0;36mTrainer._inner_training_loop\u001b[0;34m(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m   1857\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstate\u001b[38;5;241m.\u001b[39mepoch \u001b[38;5;241m=\u001b[39m epoch \u001b[38;5;241m+\u001b[39m (step \u001b[38;5;241m+\u001b[39m \u001b[38;5;241m1\u001b[39m) \u001b[38;5;241m/\u001b[39m steps_in_epoch\n\u001b[1;32m   1858\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcontrol \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_handler\u001b[38;5;241m.\u001b[39mon_step_end(args, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstate, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcontrol)\n\u001b[0;32m-> 1860\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_maybe_log_save_evaluate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtr_loss\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtrial\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mepoch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1861\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1862\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcontrol \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcallback_handler\u001b[38;5;241m.\u001b[39mon_substep_end(args, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstate, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcontrol)\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/trainer.py:2123\u001b[0m, in \u001b[0;36mTrainer._maybe_log_save_evaluate\u001b[0;34m(self, tr_loss, model, trial, epoch, ignore_keys_for_eval)\u001b[0m\n\u001b[1;32m   2117\u001b[0m             metrics \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mevaluate(\n\u001b[1;32m   2118\u001b[0m                 eval_dataset\u001b[38;5;241m=\u001b[39meval_dataset,\n\u001b[1;32m   2119\u001b[0m                 ignore_keys\u001b[38;5;241m=\u001b[39mignore_keys_for_eval,\n\u001b[1;32m   2120\u001b[0m                 metric_key_prefix\u001b[38;5;241m=\u001b[39m\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124meval_\u001b[39m\u001b[38;5;132;01m{\u001b[39;00meval_dataset_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m   2121\u001b[0m             )\n\u001b[1;32m   2122\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 2123\u001b[0m         metrics \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mevaluate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mignore_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_keys_for_eval\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2124\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_report_to_hp_search(trial, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstate\u001b[38;5;241m.\u001b[39mglobal_step, metrics)\n\u001b[1;32m   2126\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcontrol\u001b[38;5;241m.\u001b[39mshould_save:\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/trainer_seq2seq.py:78\u001b[0m, in \u001b[0;36mSeq2SeqTrainer.evaluate\u001b[0;34m(self, eval_dataset, ignore_keys, metric_key_prefix, **gen_kwargs)\u001b[0m\n\u001b[1;32m     73\u001b[0m gen_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnum_beams\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m     74\u001b[0m     gen_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnum_beams\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m gen_kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnum_beams\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mgeneration_num_beams\n\u001b[1;32m     75\u001b[0m )\n\u001b[1;32m     76\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gen_kwargs \u001b[38;5;241m=\u001b[39m gen_kwargs\n\u001b[0;32m---> 78\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mevaluate\u001b[49m\u001b[43m(\u001b[49m\u001b[43meval_dataset\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mignore_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_keys\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmetric_key_prefix\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetric_key_prefix\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/trainer.py:2819\u001b[0m, in \u001b[0;36mTrainer.evaluate\u001b[0;34m(self, eval_dataset, ignore_keys, metric_key_prefix)\u001b[0m\n\u001b[1;32m   2816\u001b[0m start_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime()\n\u001b[1;32m   2818\u001b[0m eval_loop \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprediction_loop \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39muse_legacy_prediction_loop \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mevaluation_loop\n\u001b[0;32m-> 2819\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[43meval_loop\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   2820\u001b[0m \u001b[43m    \u001b[49m\u001b[43meval_dataloader\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2821\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdescription\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mEvaluation\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2822\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# No point gathering the predictions if there are no metrics, otherwise we defer to\u001b[39;49;00m\n\u001b[1;32m   2823\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;66;43;03m# self.args.prediction_loss_only\u001b[39;49;00m\n\u001b[1;32m   2824\u001b[0m \u001b[43m    \u001b[49m\u001b[43mprediction_loss_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcompute_metrics\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   2825\u001b[0m \u001b[43m    \u001b[49m\u001b[43mignore_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_keys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2826\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmetric_key_prefix\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmetric_key_prefix\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2827\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2829\u001b[0m total_batch_size \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39meval_batch_size \u001b[38;5;241m*\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mworld_size\n\u001b[1;32m   2830\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmetric_key_prefix\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m_jit_compilation_time\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m output\u001b[38;5;241m.\u001b[39mmetrics:\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/trainer.py:3001\u001b[0m, in \u001b[0;36mTrainer.evaluation_loop\u001b[0;34m(self, dataloader, description, prediction_loss_only, ignore_keys, metric_key_prefix)\u001b[0m\n\u001b[1;32m   2998\u001b[0m         batch_size \u001b[38;5;241m=\u001b[39m observed_batch_size\n\u001b[1;32m   3000\u001b[0m \u001b[38;5;66;03m# Prediction step\u001b[39;00m\n\u001b[0;32m-> 3001\u001b[0m loss, logits, labels \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mprediction_step\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mprediction_loss_only\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mignore_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mignore_keys\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3002\u001b[0m inputs_decode \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepare_input(inputs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minput_ids\u001b[39m\u001b[38;5;124m\"\u001b[39m]) \u001b[38;5;28;01mif\u001b[39;00m args\u001b[38;5;241m.\u001b[39minclude_inputs_for_metrics \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   3004\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_torch_tpu_available():\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/trainer_seq2seq.py:213\u001b[0m, in \u001b[0;36mSeq2SeqTrainer.prediction_step\u001b[0;34m(self, model, inputs, prediction_loss_only, ignore_keys)\u001b[0m\n\u001b[1;32m    211\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m has_labels:\n\u001b[1;32m    212\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcompute_loss_context_manager():\n\u001b[0;32m--> 213\u001b[0m         outputs \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    214\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlabel_smoother \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    215\u001b[0m         loss \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlabel_smoother(outputs, inputs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlabels\u001b[39m\u001b[38;5;124m\"\u001b[39m])\u001b[38;5;241m.\u001b[39mmean()\u001b[38;5;241m.\u001b[39mdetach()\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:1190\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m   1186\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1187\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1188\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1189\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1190\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1191\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m   1192\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/models/whisper/modeling_whisper.py:1197\u001b[0m, in \u001b[0;36mWhisperForConditionalGeneration.forward\u001b[0;34m(self, input_features, decoder_input_ids, decoder_attention_mask, head_mask, decoder_head_mask, cross_attn_head_mask, encoder_outputs, past_key_values, decoder_inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m   1192\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m decoder_input_ids \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m decoder_inputs_embeds \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m   1193\u001b[0m         decoder_input_ids \u001b[38;5;241m=\u001b[39m shift_tokens_right(\n\u001b[1;32m   1194\u001b[0m             labels, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mpad_token_id, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mdecoder_start_token_id\n\u001b[1;32m   1195\u001b[0m         )\n\u001b[0;32m-> 1197\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1198\u001b[0m \u001b[43m    \u001b[49m\u001b[43minput_features\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1199\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdecoder_input_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecoder_input_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1200\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoder_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1201\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdecoder_attention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1202\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1203\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdecoder_head_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecoder_head_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1204\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcross_attn_head_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcross_attn_head_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1205\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1206\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdecoder_inputs_embeds\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecoder_inputs_embeds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1207\u001b[0m \u001b[43m    \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1208\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1209\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1210\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1211\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1212\u001b[0m lm_logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mproj_out(outputs[\u001b[38;5;241m0\u001b[39m])\n\u001b[1;32m   1214\u001b[0m loss \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:1190\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m   1186\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1187\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1188\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1189\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1190\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1191\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m   1192\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/models/whisper/modeling_whisper.py:1066\u001b[0m, in \u001b[0;36mWhisperModel.forward\u001b[0;34m(self, input_features, decoder_input_ids, decoder_attention_mask, head_mask, decoder_head_mask, cross_attn_head_mask, encoder_outputs, past_key_values, decoder_inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m   1059\u001b[0m     encoder_outputs \u001b[38;5;241m=\u001b[39m BaseModelOutput(\n\u001b[1;32m   1060\u001b[0m         last_hidden_state\u001b[38;5;241m=\u001b[39mencoder_outputs[\u001b[38;5;241m0\u001b[39m],\n\u001b[1;32m   1061\u001b[0m         hidden_states\u001b[38;5;241m=\u001b[39mencoder_outputs[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(encoder_outputs) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1062\u001b[0m         attentions\u001b[38;5;241m=\u001b[39mencoder_outputs[\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(encoder_outputs) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m2\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1063\u001b[0m     )\n\u001b[1;32m   1065\u001b[0m \u001b[38;5;66;03m# decoder outputs consists of (dec_features, past_key_value, dec_hidden, dec_attn)\u001b[39;00m\n\u001b[0;32m-> 1066\u001b[0m decoder_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecoder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1067\u001b[0m \u001b[43m    \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecoder_input_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1068\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1069\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_outputs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1070\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecoder_head_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1071\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcross_attn_head_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcross_attn_head_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1072\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1073\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdecoder_inputs_embeds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1074\u001b[0m \u001b[43m    \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1075\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1076\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1077\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1078\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1080\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m return_dict:\n\u001b[1;32m   1081\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m decoder_outputs \u001b[38;5;241m+\u001b[39m encoder_outputs\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/torch/nn/modules/module.py:1190\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m   1186\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1187\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1188\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1189\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1190\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1191\u001b[0m \u001b[38;5;66;03m# Do not call functions when jit is used\u001b[39;00m\n\u001b[1;32m   1192\u001b[0m full_backward_hooks, non_full_backward_hooks \u001b[38;5;241m=\u001b[39m [], []\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/models/whisper/modeling_whisper.py:866\u001b[0m, in \u001b[0;36mWhisperDecoder.forward\u001b[0;34m(self, input_ids, attention_mask, encoder_hidden_states, head_mask, cross_attn_head_mask, past_key_values, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m    863\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inputs_embeds \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    864\u001b[0m     inputs_embeds \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39membed_tokens(input_ids)\n\u001b[0;32m--> 866\u001b[0m attention_mask \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_prepare_decoder_attention_mask\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    867\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minput_shape\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpast_key_values_length\u001b[49m\n\u001b[1;32m    868\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    870\u001b[0m \u001b[38;5;66;03m# embed positions\u001b[39;00m\n\u001b[1;32m    871\u001b[0m positions \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39membed_positions(input_ids, past_key_values_length\u001b[38;5;241m=\u001b[39mpast_key_values_length)\n",
-      "File \u001b[0;32m~/.venv/lib/python3.8/site-packages/transformers/models/whisper/modeling_whisper.py:758\u001b[0m, in \u001b[0;36mWhisperDecoder._prepare_decoder_attention_mask\u001b[0;34m(self, attention_mask, input_shape, inputs_embeds, past_key_values_length)\u001b[0m\n\u001b[1;32m    755\u001b[0m combined_attention_mask \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    757\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m input_shape[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m] \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m--> 758\u001b[0m     combined_attention_mask \u001b[38;5;241m=\u001b[39m \u001b[43m_make_causal_mask\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    759\u001b[0m \u001b[43m        \u001b[49m\u001b[43minput_shape\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpast_key_values_length\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values_length\u001b[49m\n\u001b[1;32m    760\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdevice\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    762\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m attention_mask \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    763\u001b[0m     \u001b[38;5;66;03m# [bsz, seq_len] -> [bsz, 1, tgt_seq_len, src_seq_len]\u001b[39;00m\n\u001b[1;32m    764\u001b[0m     expanded_attn_mask \u001b[38;5;241m=\u001b[39m _expand_mask(attention_mask, inputs_embeds\u001b[38;5;241m.\u001b[39mdtype, tgt_len\u001b[38;5;241m=\u001b[39minput_shape[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m])\n",
-      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
-     ]
     }
    ],
    "source": [
@@ -1352,7 +1023,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": null,
    "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
    "metadata": {},
    "outputs": [],
@@ -1378,263 +1049,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
    "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Saving model checkpoint to ./\n",
-      "Configuration saved in ./config.json\n",
-      "Model weights saved in ./pytorch_model.bin\n",
-      "Feature extractor saved in ./preprocessor_config.json\n",
-      "tokenizer config file saved in ./tokenizer_config.json\n",
-      "Special tokens file saved in ./special_tokens_map.json\n",
-      "added tokens file saved in ./added_tokens.json\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a47d7e61b9144723a4208cc4cc492eee",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Upload file pytorch_model.bin:   0%|          | 32.0k/922M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a7eb0d82c2fd4f978981915aa2314463",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Upload file runs/Dec12_04-37-47_150-136-44-233/events.out.tfevents.1670819878.150-136-44-233.69039.0: 100%|###…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "remote: Scanning LFS files for validity, may be slow...        \n",
-      "remote: LFS file scan complete.        \n",
-      "To https://huggingface.co/kimbochen/whisper-small-jp\n",
-      "   d83a98f..0ff52f0  main -> main\n",
-      "\n",
-      "Dropping the following result as it does not have all the necessary fields:\n",
-      "{'task': {'name': 'Automatic Speech Recognition', 'type': 'automatic-speech-recognition'}, 'dataset': {'name': 'Common Voice 11.0', 'type': 'mozilla-foundation/common_voice_11_0', 'config': 'ja', 'split': 'test', 'args': 'ja'}}\n",
-      "To https://huggingface.co/kimbochen/whisper-small-jp\n",
-      "   0ff52f0..22e3a01  main -> main\n",
-      "\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'https://huggingface.co/kimbochen/whisper-small-jp/commit/0ff52f0f1d63daf816427096a83f7bbf8f3892eb'"
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "trainer.push_to_hub(**kwargs)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "4df1603c-ef35-40f1-ae57-3214441073c8",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "PyTorch: setting up devices\n"
-     ]
-    }
-   ],
-   "source": [
-    "training_args = Seq2SeqTrainingArguments(\n",
-    "    output_dir=\"./\",\n",
-    "    per_device_train_batch_size=64,\n",
-    "    gradient_accumulation_steps=1,  # increase by 2x for every 2x decrease in batch size\n",
-    "    learning_rate=1e-5,\n",
-    "    max_steps=1000,\n",
-    "    num_train_epochs=-1,\n",
-    "    gradient_checkpointing=True,\n",
-    "    fp16=True,\n",
-    "    evaluation_strategy=\"steps\",\n",
-    "    per_device_eval_batch_size=8,\n",
-    "    predict_with_generate=True,\n",
-    "    generation_max_length=225,\n",
-    "    save_steps=1000,\n",
-    "    eval_steps=1000,\n",
-    "    logging_steps=25,\n",
-    "    report_to=[\"tensorboard\"],\n",
-    "    load_best_model_at_end=True,\n",
-    "    metric_for_best_model=\"wer\",\n",
-    "    greater_is_better=False,\n",
-    "    push_to_hub=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "afc2b554-7171-48c7-95aa-b7e61b70ab20",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/ubuntu/whisper-small-jp/./ is already a clone of https://huggingface.co/kimbochen/whisper-small-jp. Make sure you pull the latest changes with `repo.git_pull()`.\n",
-      "max_steps is given, it will override any value given in num_train_epochs\n",
-      "Using cuda_amp half precision backend\n"
-     ]
-    }
-   ],
-   "source": [
-    "trainer = Seq2SeqTrainer(\n",
-    "    args=training_args,\n",
-    "    model=model,\n",
-    "    train_dataset=vectorized_datasets[\"train\"],\n",
-    "    eval_dataset=vectorized_datasets[\"test\"],\n",
-    "    data_collator=data_collator,\n",
-    "    compute_metrics=compute_metrics,\n",
-    "    tokenizer=processor,\n",
-    "    callbacks=[ShuffleCallback()],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "id": "b029a1d8-24de-46e7-b067-0f900b1db342",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Loading model from checkpoint-4000.\n",
-      "/home/ubuntu/.venv/lib/python3.8/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
-      "  warnings.warn(\n",
-      "***** Running training *****\n",
-      "  Num examples = 64000\n",
-      "  Num Epochs = 9223372036854775807\n",
-      "  Instantaneous batch size per device = 64\n",
-      "  Total train batch size (w. parallel, distributed & accumulation) = 64\n",
-      "  Gradient Accumulation steps = 1\n",
-      "  Total optimization steps = 1000\n",
-      "  Number of trainable parameters = 241734912\n",
-      "  Continuing training from checkpoint, will skip to saved global_step\n",
-      "  Continuing training from epoch 4\n",
-      "  Continuing training from global step 4000\n",
-      "  Will skip the first 4 epochs then the first 0 batches in the first epoch. If this takes a lot of time, you can add the `--ignore_data_skip` flag to your launch command, but you will resume the training on data already seen by your model.\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "01337298313740d98d3cc75b6d5e3ff7",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "0it [00:00, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Reading metadata...: 0it [00:00, ?it/s]\u001b[A\n",
-      "Reading metadata...: 6505it [00:00, 34246.80it/s]\n",
-      "The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n",
-      "\n",
-      "Reading metadata...: 6505it [00:00, 84823.64it/s]\n",
-      "\n",
-      "Reading metadata...: 6505it [00:00, 88617.62it/s]\n",
-      "\n",
-      "Reading metadata...: 6505it [00:00, 90289.78it/s]\n",
-      "\n",
-      "Reading metadata...: 6505it [00:00, 91816.92it/s]\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='4001' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1000/1000 00:00, Epoch 4/9223372036854775807]\n",
-       "    </div>\n",
-       "    <table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       " <tr style=\"text-align: left;\">\n",
-       "      <th>Step</th>\n",
-       "      <th>Training Loss</th>\n",
-       "      <th>Validation Loss</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "  </tbody>\n",
-       "</table><p>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "Training completed. Do not forget to share your model on huggingface.co/models =)\n",
-      "\n",
-      "\n",
-      "Loading best model from ./checkpoint-4000 (score: 88.31039863810469).\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "TrainOutput(global_step=4001, training_loss=8.343380785802548e-08, metrics={'train_runtime': 169.0541, 'train_samples_per_second': 378.577, 'train_steps_per_second': 5.915, 'total_flos': 7.363747084345344e+19, 'train_loss': 8.343380785802548e-08, 'epoch': 4.0})"
-      ]
-     },
-     "execution_count": 30,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "trainer.train(\"checkpoint-4000\")"
-   ]
   }
  ],
  "metadata": {

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e06d3e42c138244efef713a71edd16e7d80d9f5c735a8f6d28405049e4324d
+oid sha256:a52725380668355f0448b3218516e7537f6c679336c6c10c74fef50e1b86494e
 size 967102601

run.sh

@@ -0,0 +1,38 @@
+python run_speech_recognition_seq2seq_streaming.py \
+    --output_dir="./" \
+    --model_name_or_path="openai/whisper-small" \
+    --model_index_name="Whisper Small Japanese" \
+    --dataset_name="mozilla-foundation/common_voice_11_0" \
+    --dataset_config_name="ja" \
+    --language="japanese" \
+    --train_split_name="train+validation" \
+    --eval_split_name="test" \
+    --learning_rate="1e-5" \
+    --per_device_train_batch_size="64" \
+    --per_device_eval_batch_size="32" \
+    --max_steps="1000" \
+    --warmup_steps="500" \
+    --logging_steps="25" \
+    --evaluation_strategy="steps" \
+    --eval_steps="200" \
+    --save_strategy="steps" \
+    --save_steps="200" \
+    --generation_max_length="225" \
+    --length_column_name="input_length" \
+    --max_duration_in_seconds="30" \
+    --text_column_name="sentence" \
+    --freeze_feature_encoder="False" \
+    --report_to="tensorboard" \
+    --metric_for_best_model="wer" \
+    --greater_is_better="False" \
+    --load_best_model_at_end \
+    --gradient_checkpointing \
+    --fp16 \
+    --overwrite_output_dir \
+    --do_train \
+    --do_eval \
+    --predict_with_generate \
+    --do_normalize_eval \
+    --streaming \
+    --use_auth_token \
+    --push_to_hub

run_speech_recognition_seq2seq_streaming.py

@@ -0,0 +1,644 @@
+#!/usr/bin/env python
+# coding=utf-8
+# Copyright 2022 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Fine-tuning the library models for sequence to sequence speech recognition
+with 🤗 Datasets' streaming mode.
+"""
+# You can also adapt this script for your own sequence to sequence speech
+# recognition task. Pointers for this are left as comments.
+
+import logging
+import os
+import sys
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Union
+
+import datasets
+import torch
+from datasets import DatasetDict, IterableDatasetDict, interleave_datasets, load_dataset
+from torch.utils.data import IterableDataset
+
+import evaluate
+import transformers
+from transformers import (
+    AutoConfig,
+    AutoFeatureExtractor,
+    AutoModelForSpeechSeq2Seq,
+    AutoProcessor,
+    AutoTokenizer,
+    HfArgumentParser,
+    Seq2SeqTrainer,
+    Seq2SeqTrainingArguments,
+    TrainerCallback,
+    set_seed,
+)
+from transformers.models.whisper.english_normalizer import BasicTextNormalizer
+from transformers.trainer_pt_utils import IterableDatasetShard
+from transformers.trainer_utils import get_last_checkpoint, is_main_process
+from transformers.utils import check_min_version, send_example_telemetry
+from transformers.utils.versions import require_version
+
+from fugashi import Tagger
+import warnings
+import logging
+
+warnings.simplefilter(action='ignore', category=FutureWarning)
+logging.basicConfig(level=logging.ERROR)
+
+
+# Will error if the minimal version of Transformers is not installed. Remove at your own risks.
+check_min_version("4.25.0.dev0")
+
+require_version("datasets>=1.18.2", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
+
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class ModelArguments:
+    """
+    Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
+    """
+
+    model_name_or_path: str = field(
+        metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
+    )
+    config_name: Optional[str] = field(
+        default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
+    )
+    tokenizer_name: Optional[str] = field(
+        default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
+    )
+    feature_extractor_name: Optional[str] = field(
+        default=None, metadata={"help": "feature extractor name or path if not the same as model_name"}
+    )
+    cache_dir: Optional[str] = field(
+        default=None,
+        metadata={"help": "Where to store the pretrained models downloaded from huggingface.co"},
+    )
+    use_fast_tokenizer: bool = field(
+        default=True,
+        metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
+    )
+    model_revision: str = field(
+        default="main",
+        metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
+    )
+    use_auth_token: bool = field(
+        default=False,
+        metadata={
+            "help": (
+                "Will use the token generated when running `huggingface-cli login` (necessary to use this script "
+                "with private models)."
+            )
+        },
+    )
+    freeze_feature_encoder: bool = field(
+        default=True, metadata={"help": "Whether to freeze the feature encoder layers of the model."}
+    )
+    freeze_encoder: bool = field(
+        default=False, metadata={"help": "Whether to freeze the entire encoder of the seq2seq model."}
+    )
+    forced_decoder_ids: List[List[int]] = field(
+        default=None,
+        metadata={
+            "help": (
+                "A list of pairs of integers which indicates a mapping from generation indices to token indices "
+                "that will be forced before sampling. For example, [[0, 123]] means the first generated token "
+                "will always be a token of index 123."
+            )
+        },
+    )
+    suppress_tokens: List[int] = field(
+        default=None, metadata={"help": "A list of tokens that will be suppressed at generation."}
+    )
+    model_index_name: str = field(default=None, metadata={"help": "Pretty name for the model card."})
+
+
+@dataclass
+class DataTrainingArguments:
+    """
+    Arguments pertaining to what data we are going to input our model for training and eval.
+    """
+
+    dataset_name: str = field(
+        default=None, metadata={"help": "The name of the dataset to use (via the datasets library)."}
+    )
+    dataset_config_name: Optional[str] = field(
+        default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
+    )
+    text_column: Optional[str] = field(
+        default=None,
+        metadata={"help": "The name of the column in the datasets containing the full texts (for summarization)."},
+    )
+    max_train_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": (
+                "For debugging purposes or quicker training, truncate the number of training examples to this "
+                "value if set."
+            )
+        },
+    )
+    max_eval_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": (
+                "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
+                "value if set."
+            )
+        },
+    )
+    audio_column_name: str = field(
+        default="audio",
+        metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
+    )
+    text_column_name: str = field(
+        default="text",
+        metadata={"help": "The name of the dataset column containing the text data. Defaults to 'text'"},
+    )
+    max_duration_in_seconds: float = field(
+        default=20.0,
+        metadata={
+            "help": (
+                "Truncate audio files that are longer than `max_duration_in_seconds` seconds to"
+                " 'max_duration_in_seconds`"
+            )
+        },
+    )
+    min_duration_in_seconds: float = field(
+        default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
+    )
+    train_split_name: str = field(
+        default="train",
+        metadata={
+            "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
+        },
+    )
+    eval_split_name: str = field(
+        default="test",
+        metadata={
+            "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
+        },
+    )
+    do_lower_case: bool = field(
+        default=False,
+        metadata={"help": "Whether the target text should be lower cased."},
+    )
+    do_remove_punctuation: bool = field(
+        default=False,
+        metadata={"help": "Whether the target text should be striped of punctuation."},
+    )
+    do_normalize_eval: bool = field(
+        default=True,
+        metadata={"help": "Whether to normalise the references and predictions in the eval WER calculation."},
+    )
+    language: str = field(
+        default=None,
+        metadata={
+            "help": (
+                "Language for multilingual fine-tuning. This argument should be set for multilingual fine-tuning "
+                "only. For English speech recognition, it should be set to `None`."
+            )
+        },
+    )
+    task: str = field(
+        default="transcribe",
+        metadata={"help": "Task, either `transcribe` for speech recognition or `translate` for speech translation."},
+    )
+    shuffle_buffer_size: Optional[int] = field(
+        default=500,
+        metadata={
+            "help": (
+                "The number of streamed examples to download before shuffling them. The large the buffer, "
+                "the closer it is to real offline shuffling."
+            )
+        },
+    )
+    streaming: bool = field(
+        default=True,
+        metadata={"help": "Whether to use streaming mode to load and pre-process the data."},
+    )
+
+
+@dataclass
+class DataCollatorSpeechSeq2SeqWithPadding:
+    """
+    Data collator that will dynamically pad the inputs received.
+    Args:
+        processor ([`WhisperProcessor`])
+            The processor used for processing the data.
+        decoder_start_token_id (`int`)
+            The begin-of-sentence of the decoder.
+    """
+
+    processor: Any
+    decoder_start_token_id: int
+
+    def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
+        # split inputs and labels since they have to be of different lengths and need
+        # different padding methods
+        model_input_name = self.processor.model_input_names[0]
+        input_features = [{model_input_name: feature[model_input_name]} for feature in features]
+        label_features = [{"input_ids": feature["labels"]} for feature in features]
+
+        batch = self.processor.feature_extractor.pad(input_features, return_tensors="pt")
+
+        labels_batch = self.processor.tokenizer.pad(label_features, return_tensors="pt")
+
+        # replace padding with -100 to ignore loss correctly
+        labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)
+
+        # if bos token is appended in previous tokenization step,
+        # cut bos token here as it's append later anyways
+        if (labels[:, 0] == self.decoder_start_token_id).all().cpu().item():
+            labels = labels[:, 1:]
+
+        batch["labels"] = labels
+
+        return batch
+
+
+def load_maybe_streaming_dataset(dataset_name, dataset_config_name, split="train", streaming=True, **kwargs):
+    """
+    Utility function to load a dataset in streaming mode. For datasets with multiple splits,
+    each split is loaded individually and then splits combined by taking alternating examples from
+    each (interleaving).
+    """
+    if "+" in split:
+        # load multiple splits separated by the `+` symbol with streaming mode
+        dataset_splits = [
+            load_dataset(dataset_name, dataset_config_name, split=split_name, streaming=streaming, **kwargs)
+            for split_name in split.split("+")
+        ]
+        # interleave multiple splits to form one dataset
+        interleaved_dataset = interleave_datasets(dataset_splits)
+        return interleaved_dataset
+    else:
+        # load a single split *with* streaming mode
+        dataset = load_dataset(dataset_name, dataset_config_name, split=split, streaming=streaming, **kwargs)
+        return dataset
+
+
+def main():
+    # 1. Parse input arguments
+    # See all possible arguments in src/transformers/training_args.py
+    # or by passing the --help flag to this script.
+    # We now keep distinct sets of args, for a cleaner separation of concerns.
+    parser = HfArgumentParser((ModelArguments, DataTrainingArguments, Seq2SeqTrainingArguments))
+
+    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
+        # If we pass only one argument to the script and it's the path to a json file,
+        # let's parse it to get our arguments.
+        model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
+    else:
+        model_args, data_args, training_args = parser.parse_args_into_dataclasses()
+
+    # Sending telemetry. Tracking the example usage helps us better allocate resources to maintain them. The
+    # information sent is the one passed as arguments along with your Python/PyTorch versions.
+    send_example_telemetry("run_speech_recognition_seq2seq_streaming", model_args, data_args)
+
+    # 2. Setup logging
+    logging.basicConfig(
+        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
+        datefmt="%m/%d/%Y %H:%M:%S",
+        handlers=[logging.StreamHandler(sys.stdout)],
+    )
+    log_level = training_args.get_process_log_level()
+    logger.setLevel(log_level)
+    datasets.utils.logging.set_verbosity(log_level)
+    transformers.utils.logging.set_verbosity(log_level)
+    transformers.utils.logging.enable_default_handler()
+    transformers.utils.logging.enable_explicit_format()
+
+    logger.setLevel(logging.INFO if is_main_process(training_args.local_rank) else logging.WARN)
+
+    # Log on each process the small summary:
+    logger.warning(
+        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
+        f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
+    )
+    logger.info(f"Training/evaluation parameters {training_args}")
+
+    # Set the verbosity to info of the Transformers logger (on main process only):
+    if is_main_process(training_args.local_rank):
+        transformers.utils.logging.set_verbosity_info()
+    logger.info("Training/evaluation parameters %s", training_args)
+
+    # 3. Detecting last checkpoint and eventually continue from last checkpoint
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None and training_args.resume_from_checkpoint is None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
+    # Set seed before initializing model.
+    set_seed(training_args.seed)
+
+    # 4. Load dataset
+    raw_datasets = IterableDatasetDict() if data_args.streaming else DatasetDict()
+
+    if training_args.do_train:
+        raw_datasets["train"] = load_maybe_streaming_dataset(
+            data_args.dataset_name,
+            data_args.dataset_config_name,
+            split=data_args.train_split_name,
+            use_auth_token=True if model_args.use_auth_token else None,
+            streaming=data_args.streaming,
+        )
+
+    if training_args.do_eval:
+        raw_datasets["eval"] = load_maybe_streaming_dataset(
+            data_args.dataset_name,
+            data_args.dataset_config_name,
+            split=data_args.eval_split_name,
+            use_auth_token=True if model_args.use_auth_token else None,
+            streaming=data_args.streaming,
+        )
+
+    raw_datasets_features = list(next(iter(raw_datasets.values())).features.keys())
+
+    if data_args.audio_column_name not in raw_datasets_features:
+        raise ValueError(
+            f"--audio_column_name '{data_args.audio_column_name}' not found in dataset '{data_args.dataset_name}'. "
+            "Make sure to set `--audio_column_name` to the correct audio column - one of "
+            f"{', '.join(raw_datasets_features)}."
+        )
+
+    if data_args.text_column_name not in raw_datasets_features:
+        raise ValueError(
+            f"--text_column_name {data_args.text_column_name} not found in dataset '{data_args.dataset_name}'. "
+            "Make sure to set `--text_column_name` to the correct text column - one of "
+            f"{', '.join(raw_datasets_features)}."
+        )
+
+    # 5. Load pretrained model, tokenizer, and feature extractor
+    #
+    # Distributed training:
+    # The .from_pretrained methods guarantee that only one local process can concurrently
+    config = AutoConfig.from_pretrained(
+        model_args.config_name if model_args.config_name else model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+
+    config.update({"forced_decoder_ids": model_args.forced_decoder_ids, "suppress_tokens": model_args.suppress_tokens})
+
+    if training_args.gradient_checkpointing:
+        config.update({"use_cache": False})
+
+    feature_extractor = AutoFeatureExtractor.from_pretrained(
+        model_args.feature_extractor_name if model_args.feature_extractor_name else model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+    tokenizer = AutoTokenizer.from_pretrained(
+        model_args.tokenizer_name if model_args.tokenizer_name else model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        use_fast=model_args.use_fast_tokenizer,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+    model = AutoModelForSpeechSeq2Seq.from_pretrained(
+        model_args.model_name_or_path,
+        config=config,
+        cache_dir=model_args.cache_dir,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+
+    if model.config.decoder_start_token_id is None:
+        raise ValueError("Make sure that `config.decoder_start_token_id` is correctly defined")
+
+    if model_args.freeze_feature_encoder:
+        model.freeze_feature_encoder()
+
+    if model_args.freeze_encoder:
+        model.freeze_encoder()
+
+    if data_args.language is not None:
+        # We only need to set the task id when the language is specified (i.e. in a multilingual setting)
+        tokenizer.set_prefix_tokens(language=data_args.language, task=data_args.task)
+
+    # 6. Resample speech dataset if necessary
+    dataset_sampling_rate = next(iter(raw_datasets.values())).features[data_args.audio_column_name].sampling_rate
+    if dataset_sampling_rate != feature_extractor.sampling_rate:
+        raw_datasets = raw_datasets.cast_column(
+            data_args.audio_column_name, datasets.features.Audio(sampling_rate=feature_extractor.sampling_rate)
+        )
+
+    # 7. Preprocessing the datasets.
+    # We need to read the audio files as arrays and tokenize the targets.
+    max_input_length = data_args.max_duration_in_seconds * feature_extractor.sampling_rate
+    min_input_length = data_args.min_duration_in_seconds * feature_extractor.sampling_rate
+    audio_column_name = data_args.audio_column_name
+    text_column_name = data_args.text_column_name
+    model_input_name = feature_extractor.model_input_names[0]
+    do_lower_case = data_args.do_lower_case
+    do_remove_punctuation = data_args.do_remove_punctuation
+    normalizer = BasicTextNormalizer()  # 'official' text normalizer from OpenAI
+
+    if data_args.max_train_samples is not None:
+        raw_datasets["train"] = (
+            raw_datasets["train"].take(data_args.max_train_samples)
+            if data_args.streaming
+            else raw_datasets["train"].select(range(data_args.max_train_samples))
+        )
+
+    if data_args.max_eval_samples is not None:
+        raw_datasets["eval"] = (
+            raw_datasets["eval"].take(data_args.max_eval_samples)
+            if data_args.streaming
+            else raw_datasets["eval"].select(range(data_args.max_eval_samples))
+        )
+
+    tagger = Tagger('-Owakati')
+    FULL2HALF = dict((i + 0xFEE0, i) for i in range(0x21, 0x7F))
+    FULL2HALF[0x3000] = 0x20
+
+    def prepare_dataset(batch):
+        # process audio
+        sample = batch[audio_column_name]
+        inputs = feature_extractor(sample["array"], sampling_rate=sample["sampling_rate"])
+        # process audio length
+        batch[model_input_name] = inputs.get(model_input_name)[0]
+        batch["input_length"] = len(sample["array"])
+
+        # process targets
+        input_str = batch[text_column_name].lower() if do_lower_case else batch[text_column_name]
+        if do_remove_punctuation:
+            input_str = normalizer(input_str).strip()
+
+        input_str = input_str.translate(FULL2HALF)
+        input_str = tagger.parse(input_str)
+
+        batch["labels"] = tokenizer(input_str).input_ids
+        return batch
+
+    with training_args.main_process_first(desc="dataset map pre-processing"):
+        vectorized_datasets = raw_datasets.map(
+            prepare_dataset,
+            remove_columns=raw_datasets_features,
+        ).with_format("torch")
+
+        if training_args.do_train and data_args.streaming:
+            # manually shuffle if streaming (done by the trainer for non-streaming)
+            vectorized_datasets["train"] = vectorized_datasets["train"].shuffle(
+                buffer_size=data_args.shuffle_buffer_size,
+                seed=training_args.seed,
+            )
+
+    # filter training data that is shorter than min_input_length or longer than
+    # max_input_length
+    def is_audio_in_length_range(length):
+        return min_input_length < length < max_input_length
+
+    if training_args.do_train:
+        vectorized_datasets["train"] = vectorized_datasets["train"].filter(
+            is_audio_in_length_range,
+            input_columns=["input_length"],
+        )
+
+    # 8. Load Metric
+    metric = evaluate.load("wer")
+    do_normalize_eval = data_args.do_normalize_eval
+
+    def compute_metrics(pred):
+        pred_ids = pred.predictions
+
+        pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
+
+        pred_str = tokenizer.batch_decode(pred_ids, skip_special_tokens=True)
+        # we do not want to group tokens when computing the metrics
+        label_str = tokenizer.batch_decode(pred.label_ids, skip_special_tokens=True)
+
+        if do_normalize_eval:
+            pred_str = [normalizer(pred) for pred in pred_str]
+            label_str = [normalizer(label) for label in label_str]
+            # filtering step to only evaluate the samples that correspond to non-zero references:
+            pred_str = [pred_str[i] for i in range(len(pred_str)) if len(label_str[i]) > 0]
+            label_str = [label_str[i] for i in range(len(label_str)) if len(label_str[i]) > 0]
+
+        wer = 100 * metric.compute(predictions=pred_str, references=label_str)
+
+        return {"wer": wer}
+
+    # 9. Create a single speech processor
+    if is_main_process(training_args.local_rank):
+        # save feature extractor, tokenizer and config
+        feature_extractor.save_pretrained(training_args.output_dir)
+        tokenizer.save_pretrained(training_args.output_dir)
+        config.save_pretrained(training_args.output_dir)
+
+    processor = AutoProcessor.from_pretrained(training_args.output_dir)
+
+    # 10. Define data collator
+    data_collator = DataCollatorSpeechSeq2SeqWithPadding(
+        processor=processor,
+        decoder_start_token_id=model.config.decoder_start_token_id,
+    )
+
+    # 11. Configure Trainer
+    # Trainer callback to reinitialise and reshuffle the streamable datasets at the beginning of each epoch
+    # Only required for streaming: Trainer automatically shuffles non-streaming datasets
+    class ShuffleCallback(TrainerCallback):
+        def on_epoch_begin(self, args, state, control, train_dataloader, **kwargs):
+            if isinstance(train_dataloader.dataset, IterableDatasetShard):
+                pass  # set_epoch() is handled by the Trainer
+            elif isinstance(train_dataloader.dataset, IterableDataset):
+                train_dataloader.dataset.set_epoch(train_dataloader.dataset._epoch + 1)
+
+    # Initialize Trainer
+    trainer = Seq2SeqTrainer(
+        model=model,
+        args=training_args,
+        train_dataset=vectorized_datasets["train"] if training_args.do_train else None,
+        eval_dataset=vectorized_datasets["eval"] if training_args.do_eval else None,
+        tokenizer=feature_extractor,
+        data_collator=data_collator,
+        compute_metrics=compute_metrics if training_args.predict_with_generate else None,
+        callbacks=[ShuffleCallback()] if data_args.streaming else None,
+    )
+
+    # 12. Training
+    if training_args.do_train:
+        checkpoint = None
+        if training_args.resume_from_checkpoint is not None:
+            checkpoint = training_args.resume_from_checkpoint
+        elif last_checkpoint is not None:
+            checkpoint = last_checkpoint
+        train_result = trainer.train(resume_from_checkpoint=checkpoint)
+        trainer.save_model()  # Saves the feature extractor too for easy upload
+
+        metrics = train_result.metrics
+        if data_args.max_train_samples:
+            metrics["train_samples"] = data_args.max_train_samples
+        trainer.log_metrics("train", metrics)
+        trainer.save_metrics("train", metrics)
+        trainer.save_state()
+
+    # 13. Evaluation
+    results = {}
+    if training_args.do_eval:
+        logger.info("*** Evaluate ***")
+        metrics = trainer.evaluate(
+            metric_key_prefix="eval",
+            max_length=training_args.generation_max_length,
+            num_beams=training_args.generation_num_beams,
+        )
+        if data_args.max_eval_samples:
+            metrics["eval_samples"] = data_args.max_eval_samples
+
+        trainer.log_metrics("eval", metrics)
+        trainer.save_metrics("eval", metrics)
+
+    # 14. Write Training Stats
+    kwargs = {
+        "finetuned_from": model_args.model_name_or_path,
+        "tasks": "automatic-speech-recognition",
+        "tags": "whisper-event",
+    }
+    if data_args.dataset_name is not None:
+        kwargs["dataset_tags"] = data_args.dataset_name
+        if data_args.dataset_config_name is not None:
+            kwargs["dataset"] = f"{data_args.dataset_name} {data_args.dataset_config_name}"
+        else:
+            kwargs["dataset"] = data_args.dataset_name
+        if "common_voice" in data_args.dataset_name:
+            kwargs["language"] = data_args.dataset_config_name[:2]
+        if model_args.model_index_name is not None:
+            kwargs["model_name"] = model_args.model_index_name
+
+    if training_args.push_to_hub:
+        trainer.push_to_hub(**kwargs)
+    else:
+        trainer.create_model_card(**kwargs)
+
+    return results
+
+
+if __name__ == "__main__":
+    main()

runs/Dec12_18-34-55_129-213-131-105/1670870162.6479564/events.out.tfevents.1670870162.129-213-131-105.68826.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece26b007dd4241195f82f895387be76fc7cc1c070b15d6f83ae2cc25b41f8c6
+size 5865

runs/Dec12_18-34-55_129-213-131-105/events.out.tfevents.1670870162.129-213-131-105.68826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704f9f0cca7b13ef1f58bb28efd54ba803cdba17d54dd80adcf64079cc38ed7f
+size 5370

runs/Dec12_19-04-31_129-213-131-105/1670871909.2493246/events.out.tfevents.1670871909.129-213-131-105.451160.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b59cfc6e1d7df33976f6ce86c76510a7f41fead860dec2c69fe7cd2bf5e167
+size 5865

runs/Dec12_19-04-31_129-213-131-105/events.out.tfevents.1670871909.129-213-131-105.451160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3452ff74759aee1840801aed3d7356082411fd624c88f84ddd9ceb9bae889f6
+size 5527

runs/Dec12_20-09-15_129-213-131-105/1670875765.5760763/events.out.tfevents.1670875765.129-213-131-105.451160.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b008ba42cd993b9bd02a9144eff9cf9407ecbbeb529d55c4dc9a1ec94b44df3
+size 5865

runs/Dec12_20-09-15_129-213-131-105/events.out.tfevents.1670875765.129-213-131-105.451160.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdab32f753d53633663898b271753c8b3b5ea9e96877ae405591009e23d7a94
+size 4287

runs/Dec12_20-11-02_129-213-131-105/1670875868.8091414/events.out.tfevents.1670875868.129-213-131-105.451160.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ebc2f17552904c895f3c671b4094d006a214efda5d17991beffa79c33e8d6d
+size 5865

runs/Dec12_20-11-02_129-213-131-105/events.out.tfevents.1670875868.129-213-131-105.451160.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ef5fa9c89efaa03ab70ca5b5048b390e7834395f47878d50d4b6c88c5963a5
+size 4287

runs/Dec12_20-13-20_129-213-131-105/1670876009.054387/events.out.tfevents.1670876009.129-213-131-105.983201.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d78faf345393965670df0c13ba215d9d2f3388530185c1388dda5a8fa750dc
+size 5865

runs/Dec12_20-13-20_129-213-131-105/events.out.tfevents.1670876009.129-213-131-105.983201.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b488dc85e8c956dad5b3e36797db99372014a9dc6d5b6a04273fa276526b714b
+size 4903

runs/Dec12_21-41-07_129-213-131-105/1670881275.6468236/events.out.tfevents.1670881275.129-213-131-105.1284650.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfec8cffe4dc0c9cab5530627cb8e095f271d05e9e92a21b424b32ae423e8f49
+size 5871

runs/Dec12_21-41-07_129-213-131-105/events.out.tfevents.1670881275.129-213-131-105.1284650.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a93dc6d2dfd1ac5560c91f552c89c96897229798b978c8df009d41553c206e9
+size 4266

runs/Dec12_21-43-12_129-213-131-105/1670881400.3312242/events.out.tfevents.1670881400.129-213-131-105.1319036.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a8322f4fb98acacd534d77bca4396a48dc39c5c52ff7aca9cf34b75fe67bf8
+size 5871

runs/Dec12_21-43-12_129-213-131-105/events.out.tfevents.1670881400.129-213-131-105.1319036.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b878099c11902d0b4199ee621f3a5da722a287c0f380503b446684af2e9dc233
+size 4265

runs/Dec12_21-47-11_129-213-131-105/1670881639.3589363/events.out.tfevents.1670881639.129-213-131-105.1364959.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeab408d92a5d13a0ba12c052c4f63d7fd4000ddd0547a93a98e06e0ded2b8c9
+size 5871

runs/Dec12_21-47-11_129-213-131-105/events.out.tfevents.1670881639.129-213-131-105.1364959.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bc02edeb3a6602e541887d81fa5dcd7ffa46c2e2fb356d90f01b73977763eb
+size 4577

runs/Dec12_21-54-54_129-213-131-105/1670882102.7244208/events.out.tfevents.1670882102.129-213-131-105.1405782.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcce00ed71b81568f3e4404a3337617a043299eeab15de4aed07163ec387333
+size 5871

runs/Dec12_21-54-54_129-213-131-105/events.out.tfevents.1670882102.129-213-131-105.1405782.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9553563c509a988e7f213ee237136fa3c489c62602abaaa1cacafe7558aff9b
+size 5825

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728d6cd7b154a86029fc38c737217977eb35dd910ed073d6628129742d876d7e
+oid sha256:2f9ea5f3e1c3a7983069a437425a4e13e3bbae038786ac8163dfd02cc6f10148
 size 3579