update model

Generate.ipynb

@@ -9,7 +9,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "50bf0f78f5f044dd8be6b181b2cb0949",
+       "model_id": "7afc85b57ea24d31a2fdcc2b1f5c9ace",
        "version_major": 2,
        "version_minor": 0
       },
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "38bdf299-f60d-43ea-9230-df1be861e406",
    "metadata": {},
    "outputs": [
@@ -43,7 +43,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c495fe2f4a44499fb32751d60ac1488e",
+       "model_id": "18cae671f8fd4f9baac804c91fee03bf",
        "version_major": 2,
        "version_minor": 0
       },
@@ -62,14 +62,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 22,
    "id": "75b32151-eb53-4476-8c1f-7e6da72e173e",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0f019d1f864b4b56af5c828588fd89bf",
+       "model_id": "0611b2fa6cf740d6925d03cf3ba525a2",
        "version_major": 2,
        "version_minor": 0
       },
@@ -88,7 +88,7 @@
     "  return {\"vocab\": [vocab], \"all_text\": [all_text]}\n",
     "\n",
     "vocabs = ds.map(extract_all_chars, batched=True, batch_size=-1, keep_in_memory=True, remove_columns=ds.column_names[\"train\"])\n",
-    "vocab_list = list(set(vocabs[\"train\"][\"vocab\"][0]) | set(vocabs[\"train\"][\"vocab\"][0]))\n",
+    "vocab_list = list(set(vocabs[\"train\"][\"vocab\"][0]))\n",
     "vocab_dict = {v: k for k, v in enumerate(vocab_list)}\n",
     "vocab_dict[\"|\"] = vocab_dict[\" \"]\n",
     "del vocab_dict[\" \"]\n",
@@ -102,7 +102,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 23,
    "id": "d214872e-d4b1-4aa7-be07-8a1591961968",
    "metadata": {},
    "outputs": [],
@@ -111,14 +111,14 @@
     "from transformers import Wav2Vec2FeatureExtractor\n",
     "from transformers import Wav2Vec2Processor\n",
     "\n",
-    "tokenizer = Wav2Vec2CTCTokenizer(\"./vocab.json\", unk_token=\"[UNK]\", pad_token=\"[PAD]\", word_delimiter_token=\"|\")\n",
+    "tokenizer = Wav2Vec2CTCTokenizer(\"./vocab.json\", unk_token=\"[UNK]\", pad_token=\"[PAD]\", word_delimiter_token=\" \")\n",
     "feature_extractor = Wav2Vec2FeatureExtractor(feature_size=1, sampling_rate=16000, padding_value=0.0, do_normalize=True, return_attention_mask=False)\n",
     "processor = Wav2Vec2Processor(feature_extractor=feature_extractor, tokenizer=tokenizer)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 24,
    "id": "e906c45f-6971-43c3-ad0a-b13363100bdf",
    "metadata": {},
    "outputs": [],
@@ -137,7 +137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 25,
    "id": "8c083db6-eab5-4f25-9a08-eab50d2d30ac",
    "metadata": {},
    "outputs": [
@@ -151,7 +151,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3b36aee8ffc44253a8381da4d0f4c362",
+       "model_id": "ae21f7b6a50241e4ab4dd2b5c7c5689c",
        "version_major": 2,
        "version_minor": 0
       },
@@ -169,7 +169,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 26,
    "id": "50c9a6ad-9e79-4a1c-a5ce-6e1f73a96e4d",
    "metadata": {},
    "outputs": [],
@@ -242,7 +242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 27,
    "id": "1025ffdf-cb83-4895-89ab-a98bc3fab642",
    "metadata": {},
    "outputs": [],
@@ -253,7 +253,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 35,
    "id": "71351cf4-6d00-40ae-89cc-cedb87073625",
    "metadata": {},
    "outputs": [
@@ -353,10 +353,10 @@
       "}\n",
       "\n",
       "loading weights file https://huggingface.co/facebook/wav2vec2-base/resolve/main/pytorch_model.bin from cache at /home/sharpcoder/.cache/huggingface/transformers/ef45231897ce572a660ebc5a63d3702f1a6041c4c5fb78cbec330708531939b3.fcae05302a685f7904c551c8ea571e8bc2a2c4a1777ea81ad66e47f7883a650a\n",
-      "Some weights of the model checkpoint at facebook/wav2vec2-base were not used when initializing Wav2Vec2ForCTC: ['project_q.bias', 'project_hid.bias', 'quantizer.codevectors', 'project_q.weight', 'quantizer.weight_proj.weight', 'quantizer.weight_proj.bias', 'project_hid.weight']\n",
+      "Some weights of the model checkpoint at facebook/wav2vec2-base were not used when initializing Wav2Vec2ForCTC: ['project_hid.bias', 'quantizer.weight_proj.bias', 'project_q.weight', 'project_hid.weight', 'quantizer.weight_proj.weight', 'quantizer.codevectors', 'project_q.bias']\n",
       "- This IS expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
       "- This IS NOT expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
-      "Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-base and are newly initialized: ['lm_head.bias', 'lm_head.weight']\n",
+      "Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-base and are newly initialized: ['lm_head.weight', 'lm_head.bias']\n",
       "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
      ]
     }
@@ -391,11 +391,11 @@
     "from transformers import Trainer\n",
     "\n",
     "training_args = TrainingArguments(\n",
-    "  output_dir=\"sharpcoder/wav2vec2_bjorn\",\n",
+    "  output_dir=\"./\",\n",
     "  group_by_length=True,\n",
     "  per_device_train_batch_size=8,\n",
     "  evaluation_strategy=\"steps\",\n",
-    "  num_train_epochs=30,\n",
+    "  num_train_epochs=3,\n",
     "  fp16=False,\n",
     "  gradient_checkpointing=True,\n",
     "  save_steps=500,\n",
@@ -431,17 +431,11 @@
       "The following columns in the training set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.\n",
       "***** Running training *****\n",
       "  Num examples = 1\n",
-      "  Num Epochs = 30\n",
+      "  Num Epochs = 3\n",
       "  Instantaneous batch size per device = 8\n",
       "  Total train batch size (w. parallel, distributed & accumulation) = 8\n",
       "  Gradient Accumulation steps = 1\n",
-      "  Total optimization steps = 30\n",
-      "/home/sharpcoder/.local/lib/python3.10/site-packages/transformers/feature_extraction_utils.py:158: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at  ../torch/csrc/utils/tensor_new.cpp:210.)\n",
-      "  tensor = as_tensor(value)\n",
-      "/home/sharpcoder/.local/lib/python3.10/site-packages/transformers/models/wav2vec2/modeling_wav2vec2.py:882: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').\n",
-      "  return (input_length - kernel_size) // stride + 1\n",
-      "/home/sharpcoder/.local/lib/python3.10/site-packages/torch/autocast_mode.py:162: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling\n",
-      "  warnings.warn('User provided device_type of \\'cuda\\', but CUDA is not available. Disabling')\n"
+      "  Total optimization steps = 3\n"
      ]
     },
     {
@@ -450,8 +444,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='30' max='30' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [30/30 00:29, Epoch 30/30]\n",
+       "      <progress value='3' max='3' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [3/3 00:02, Epoch 3/3]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -486,7 +480,7 @@
     {
      "data": {
       "text/plain": [
-       "TrainOutput(global_step=30, training_loss=7.301008097330729, metrics={'train_runtime': 30.6312, 'train_samples_per_second': 0.979, 'train_steps_per_second': 0.979, 'total_flos': 943749864316800.0, 'train_loss': 7.301008097330729, 'epoch': 30.0})"
+       "TrainOutput(global_step=3, training_loss=10.471563975016275, metrics={'train_runtime': 3.8966, 'train_samples_per_second': 0.77, 'train_steps_per_second': 0.77, 'total_flos': 94374986431680.0, 'train_loss': 10.471563975016275, 'epoch': 3.0})"
       ]
      },
      "execution_count": 46,
@@ -501,17 +495,17 @@
   {
    "cell_type": "code",
    "execution_count": 47,
-   "id": "70866f1f-3745-4e68-acd5-f50b6eff348b",
+   "id": "333d43cf-add3-4d78-bbca-b44c638519fe",
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Saving model checkpoint to sharpcoder/wav2vec2_bjorn\n",
-      "Configuration saved in sharpcoder/wav2vec2_bjorn/config.json\n",
-      "Model weights saved in sharpcoder/wav2vec2_bjorn/pytorch_model.bin\n",
-      "Configuration saved in sharpcoder/wav2vec2_bjorn/preprocessor_config.json\n"
+      "Saving model checkpoint to ./\n",
+      "Configuration saved in ./config.json\n",
+      "Model weights saved in ./pytorch_model.bin\n",
+      "Configuration saved in ./preprocessor_config.json\n"
      ]
     },
     {
@@ -521,18 +515,20 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "Input \u001b[0;32mIn [47]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpush_to_hub\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+      "Input \u001b[0;32mIn [47]\u001b[0m, in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpush_to_hub\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhub_model_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msharpcoder/wav2vec2_bjorn\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
       "File \u001b[0;32m~/.local/lib/python3.10/site-packages/transformers/trainer.py:2677\u001b[0m, in \u001b[0;36mTrainer.push_to_hub\u001b[0;34m(self, commit_message, blocking, **kwargs)\u001b[0m\n\u001b[1;32m   2674\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[39mis_world_process_zero():\n\u001b[1;32m   2675\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[0;32m-> 2677\u001b[0m git_head_commit_url \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrepo\u001b[49m\u001b[38;5;241m.\u001b[39mpush_to_hub(commit_message\u001b[38;5;241m=\u001b[39mcommit_message, blocking\u001b[38;5;241m=\u001b[39mblocking)\n\u001b[1;32m   2678\u001b[0m \u001b[38;5;66;03m# push separately the model card to be independant from the rest of the model\u001b[39;00m\n\u001b[1;32m   2679\u001b[0m \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[39mshould_save:\n",
       "\u001b[0;31mAttributeError\u001b[0m: 'Trainer' object has no attribute 'repo'"
      ]
     }
    ],
-   "source": []
+   "source": [
+    "trainer.push_to_hub(hub_model_id=\"sharpcoder/wav2vec2_bjorn\")"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "333d43cf-add3-4d78-bbca-b44c638519fe",
+   "id": "a5cb9a88-2443-4bd9-85ac-12bf80a9e325",
    "metadata": {},
    "outputs": [],
    "source": []

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873bf552da3de5ce2fc1efbe234017f06cf7b9b70812d408585136c69486cb81
+oid sha256:ea220cc133930f98791c7b7a1d76d68b159241b625a40a783d4e05d2c93c11d7
 size 377667031

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b61aecf82c993254e7b0fbeb1c240469688a2bf27cd91d288ef05824cd7c911
-size 2799
+oid sha256:19c7738f5655571cd7c062b8a732e09ad439c7c98c6a054da91449f8906026bf
+size 2735

vocab.json

@@ -1 +1 @@
-{"w": 0, "y": 1, "m": 2, "i": 3, "e": 4, "s": 5, "r": 6, "p": 7, "n": 8, "a": 9, "h": 10, ".": 11, "j": 12, "b": 13, "d": 14, "l": 15, "o": 16, "|": 17, "[UNK]": 18, "[PAD]": 19}
+{"w": 0, "a": 1, "o": 3, "e": 4, "j": 5, "n": 6, "p": 7, "l": 8, ".": 9, "i": 10, "b": 11, "d": 12, "h": 13, "r": 14, "y": 15, "m": 16, "s": 17, "|": 2, "[UNK]": 18, "[PAD]": 19}