Training in progress, step 1000

fine-tune-whisper-non-streaming-id-augmented.ipynb

@@ -155,408 +155,11 @@
    "id": "d087b451",
    "metadata": {},
    "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f06040b99e3a496a8b6a16cf575f5fe4",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading builder script:   0%|          | 0.00/8.30k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "51c2249ae17f4e429c1673af03eea9e5",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading readme:   0%|          | 0.00/12.2k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7a58d7f740cb4a37aab92c2991882a94",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading extra modules:   0%|          | 0.00/3.44k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5b8e88450d8a411a8b6c52e1c77d50fc",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading extra modules:   0%|          | 0.00/60.9k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading and preparing dataset common_voice_11_0/vi to /home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/vi/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f...\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b76582cd2e5547f29eaba1f558f30bf0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/12.2k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "81291c5ad37f4c03a40aaf6ba2e32604",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data files:   0%|          | 0/5 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bca9e66a222b4ffc86f7bb4fbacabdc1",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/76.3M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "eef674aee9d5483799efeaea18d745b2",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/5.54M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "57657b868c554ee4ac2abab4e8ed7ddc",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/33.9M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "74497f7b338b46a2a53b4c3fbbdd5749",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/274M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e6f531a4fcee44fd961ac763e2aa2b9b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/10.4M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "316ae0693cc6435e8216509394cc3361",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Extracting data files:   0%|          | 0/5 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "cb80410a982c418c8154892029ba9eaa",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data files:   0%|          | 0/5 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c66ce3d597764ab2a448778c0c663c8e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/562k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ecba3e1244db47a0844d26bdd99dbb13",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/53.3k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "eea8dd83dc404e398ffb189e22e480bb",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/272k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f6e7163feffd4bf8812c6c0319832fa6",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/2.52M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "cb1db21354f14d26baf884b6095cdc94",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading data:   0%|          | 0.00/74.7k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3abc46d3685c432f827dabab6dd13ffb",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Extracting data files:   0%|          | 0/5 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating train split: 0 examples [00:00, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Reading metadata...: 2525it [00:00, 140488.93it/s]\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating validation split: 0 examples [00:00, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "Reading metadata...: 248it [00:00, 133597.15it/s]\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating test split: 0 examples [00:00, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\n",
-      "Reading metadata...: 1237it [00:00, 141122.10it/s]\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating other split: 0 examples [00:00, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\n",
-      "Reading metadata...: 11476it [00:00, 144676.38it/s]\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Generating invalidated split: 0 examples [00:00, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\n",
-      "\n",
-      "Reading metadata...: 337it [00:00, 119250.86it/s][A\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Dataset common_voice_11_0 downloaded and prepared to /home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/vi/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f. Subsequent calls will reuse this data.\n"
-     ]
-    },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
+      "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/vi/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n",
       "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/vi/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n"
      ]
     },
@@ -667,26 +270,11 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "bc77d7bb-f9e2-47f5-b663-30f7a4321ce5",
-   "metadata": {
-    "id": "bc77d7bb-f9e2-47f5-b663-30f7a4321ce5"
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "56fc56162a2848afaee1d9943a8c545f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/185k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "id": "bc77d7bb-f9e2-47f5-b663-30f7a4321ce5",
+   "metadata": {
+    "id": "bc77d7bb-f9e2-47f5-b663-30f7a4321ce5"
+   },
+   "outputs": [],
    "source": [
     "from transformers import WhisperFeatureExtractor\n",
     "\n",
@@ -724,92 +312,7 @@
     "id": "c7b07f9b-ae0e-4f89-98f0-0c50d432eab6",
     "outputId": "5c004b44-86e7-4e00-88be-39e0af5eed69"
    },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3d2f8de076bd4fbb8e777da01a5bff36",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/830 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "22c630ec1f564e16b4d2066702666490",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/1.04M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2f4cb16bef8e45f5b8abf176d675fe98",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/494k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5c3601ab893747c398323f80faa415d1",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/52.7k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "424550d6926c44cf85dfb8b538cbc450",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/2.11k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d263b9aaed5d4b9e941798363994658c",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/2.06k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from transformers import WhisperTokenizer\n",
     "\n",
@@ -914,7 +417,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "id": "4c79b333",
    "metadata": {},
    "outputs": [],
@@ -940,7 +443,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "id": "c085911c-a10a-41ef-8874-306e0503e9bb",
    "metadata": {},
    "outputs": [],
@@ -978,23 +481,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "id": "db271164",
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "832b0412dca04466997f93b4191ca019",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/2773 [00:00<?, ?ex/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Loading cached processed dataset at /home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/vi/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-43c2297beff94678.arrow\n"
+     ]
     }
    ],
    "source": [
@@ -1003,28 +499,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "id": "b459b0c5",
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "614c79a32b6d422a986d2c3965d36113",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/2773 [00:00<?, ?ex/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Loading cached processed dataset at /home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/vi/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-4ea982ccf5dc2951.arrow\n"
+     ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c61eb8793f7d4a3ab831ca55790b311a",
+       "model_id": "01fdf7e3e86f4080b11126a6ec744788",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1050,7 +539,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "id": "01cb25ef-4bb0-4325-9461-f59198acadf6",
    "metadata": {},
    "outputs": [],
@@ -1071,23 +560,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac",
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "de8736cfcc9047258e38bd0bb6c820a6",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/3 [00:00<?, ?ba/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Loading cached processed dataset at /home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/vi/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-93491e8b5f5bd854.arrow\n"
+     ]
     }
    ],
    "source": [
@@ -1167,7 +649,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5",
    "metadata": {
     "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5"
@@ -1219,7 +701,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 15,
    "id": "fc834702-c0d3-4a96-b101-7b87be32bf42",
    "metadata": {
     "id": "fc834702-c0d3-4a96-b101-7b87be32bf42"
@@ -1252,41 +734,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 16,
    "id": "b22b4011-f31f-4b57-b684-c52332f92890",
    "metadata": {
     "id": "b22b4011-f31f-4b57-b684-c52332f92890"
    },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "cb228b59a10f45bc860a59f7f96b085b",
-       "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"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "36844d00e5864685a7913b31a3510284",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading builder script:   0%|          | 0.00/5.60k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "import evaluate\n",
     "\n",
@@ -1315,7 +768,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 17,
    "id": "23959a70-22d0-4ffe-9fa1-72b61e75bb52",
    "metadata": {
     "id": "23959a70-22d0-4ffe-9fa1-72b61e75bb52"
@@ -1369,41 +822,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
    "metadata": {
     "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f"
    },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9c0d9c343202473290cce99917b65ea0",
-       "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": "e0d6c82f82ed4aa292d1fbee51ebb865",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/3.06G [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "from transformers import WhisperForConditionalGeneration\n",
     "\n",
@@ -1422,7 +846,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "id": "62038ba3-88ed-4fce-84db-338f50dcd04f",
    "metadata": {
     "id": "62038ba3-88ed-4fce-84db-338f50dcd04f"
@@ -1456,7 +880,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 20,
    "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a",
    "metadata": {
     "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a"
@@ -1469,17 +893,17 @@
     "    output_dir=\"./\",\n",
     "    per_device_train_batch_size=32,\n",
     "    gradient_accumulation_steps=1,  # increase by 2x for every 2x decrease in batch size\n",
-    "    learning_rate=5e-5,\n",
-    "    warmup_steps=250,\n",
-    "    max_steps=2500,\n",
+    "    learning_rate=1e-5,\n",
+    "    warmup_steps=500,\n",
+    "    max_steps=5000,\n",
     "    gradient_checkpointing=True,\n",
     "    fp16=True,\n",
     "    evaluation_strategy=\"steps\",\n",
     "    per_device_eval_batch_size=16,\n",
     "    predict_with_generate=True,\n",
     "    generation_max_length=225,\n",
-    "    save_steps=500,\n",
-    "    eval_steps=500,\n",
+    "    save_steps=1000,\n",
+    "    eval_steps=1000,\n",
     "    logging_steps=25,\n",
     "    report_to=[\"tensorboard\"],\n",
     "    load_best_model_at_end=True,\n",
@@ -1513,7 +937,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 21,
    "id": "d546d7fe-0543-479a-b708-2ebabec19493",
    "metadata": {
     "id": "d546d7fe-0543-479a-b708-2ebabec19493"
@@ -1555,7 +979,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 22,
    "id": "-2zQwMfEOBJq",
    "metadata": {
     "id": "-2zQwMfEOBJq"
@@ -1608,7 +1032,7 @@
    "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
    "metadata": {
     "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
-    "scrolled": true
+    "scrolled": false
    },
    "outputs": [
     {
@@ -1620,11 +1044,11 @@
       "  warnings.warn(\n",
       "***** Running training *****\n",
       "  Num examples = 2773\n",
-      "  Num Epochs = 29\n",
+      "  Num Epochs = 58\n",
       "  Instantaneous batch size per device = 32\n",
       "  Total train batch size (w. parallel, distributed & accumulation) = 32\n",
       "  Gradient Accumulation steps = 1\n",
-      "  Total optimization steps = 2500\n",
+      "  Total optimization steps = 5000\n",
       "  Number of trainable parameters = 763857920\n"
      ]
     },
@@ -1634,8 +1058,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='501' max='2500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [ 501/2500 33:06 < 2:12:39, 0.25 it/s, Epoch 5.75/29]\n",
+       "      <progress value='1001' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [1001/5000 1:06:20 < 4:25:35, 0.25 it/s, Epoch 11.49/58]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -1643,17 +1067,20 @@
        "      <th>Step</th>\n",
        "      <th>Training Loss</th>\n",
        "      <th>Validation Loss</th>\n",
+       "      <th>Wer</th>\n",
+       "      <th>Cer</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>1000</td>\n",
+       "      <td>0.005300</td>\n",
+       "      <td>0.542897</td>\n",
+       "      <td>18.128976</td>\n",
+       "      <td>8.464310</td>\n",
+       "    </tr>\n",
        "  </tbody>\n",
-       "</table><p>\n",
-       "    <div>\n",
-       "      \n",
-       "      <progress value='77' max='78' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [77/78 10:16 < 00:08, 0.12 it/s]\n",
-       "    </div>\n",
-       "    "
+       "</table><p>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -2853,7 +2280,18 @@
       "  \"transformers_version\": \"4.26.0.dev0\",\n",
       "  \"use_cache\": false\n",
       "}\n",
-      "\n"
+      "\n",
+      "Saving model checkpoint to ./checkpoint-1000\n",
+      "Configuration saved in ./checkpoint-1000/config.json\n",
+      "Model weights saved in ./checkpoint-1000/pytorch_model.bin\n",
+      "Feature extractor saved in ./checkpoint-1000/preprocessor_config.json\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Feature extractor saved in ./preprocessor_config.json\n"
      ]
     }
    ],
@@ -2920,14 +2358,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "fleurs_results = trainer.evaluate(fleurs['test'])\n",
-    "print(fleurs_results)\n",
-    "\n",
     "cv_results = trainer.evaluate(cv['test'])\n",
-    "print(cv_results)\n",
-    "\n",
-    "lbv_results = trainer.evaluate(lbv['test'])\n",
-    "print(lbv_results)"
+    "print(cv_results)"
    ]
   },
   {
@@ -2937,34 +2369,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "evaluate.push_to_hub(\n",
-    "        model_id='Scrya/whisper-medium-id',\n",
-    "        metric_value=round(fleurs_results['eval_wer'], 2),\n",
-    "        metric_type=\"wer\",\n",
-    "        metric_name=\"WER\",\n",
-    "        dataset_name='google/fleurs',\n",
-    "        dataset_type='google/fleurs',\n",
-    "        dataset_split='test',\n",
-    "        dataset_config='id_id',\n",
-    "        task_type=\"automatic-speech-recognition\",\n",
-    "        task_name=\"Automatic Speech Recognition\",\n",
-    "        overwrite=True\n",
-    "    )\n",
-    "\n",
-    "evaluate.push_to_hub(\n",
-    "        model_id='Scrya/whisper-medium-id',\n",
-    "        metric_value=round(fleurs_results['eval_cer'], 2),\n",
-    "        metric_type=\"cer\",\n",
-    "        metric_name=\"CER\",\n",
-    "        dataset_name='google/fleurs',\n",
-    "        dataset_type='google/fleurs',\n",
-    "        dataset_split='test',\n",
-    "        dataset_config='id_id',\n",
-    "        task_type=\"automatic-speech-recognition\",\n",
-    "        task_name=\"Automatic Speech Recognition\",\n",
-    "        overwrite=True\n",
-    "    )\n",
-    "\n",
     "evaluate.push_to_hub(\n",
     "        model_id='Scrya/whisper-medium-id',\n",
     "        metric_value=round(cv_results['eval_wer'], 2),\n",
@@ -2973,7 +2377,7 @@
     "        dataset_name='mozilla-foundation/common_voice_11_0',\n",
     "        dataset_type='mozilla-foundation/common_voice_11_0',\n",
     "        dataset_split='test',\n",
-    "        dataset_config='id',\n",
+    "        dataset_config='vi',\n",
     "        task_type=\"automatic-speech-recognition\",\n",
     "        task_name=\"Automatic Speech Recognition\",\n",
     "        overwrite=True\n",
@@ -2987,35 +2391,7 @@
     "        dataset_name='mozilla-foundation/common_voice_11_0',\n",
     "        dataset_type='mozilla-foundation/common_voice_11_0',\n",
     "        dataset_split='test',\n",
-    "        dataset_config='id',\n",
-    "        task_type=\"automatic-speech-recognition\",\n",
-    "        task_name=\"Automatic Speech Recognition\",\n",
-    "        overwrite=True\n",
-    "    )\n",
-    "\n",
-    "evaluate.push_to_hub(\n",
-    "        model_id='Scrya/whisper-medium-id',\n",
-    "        metric_value=round(lbv_results['eval_wer'], 2),\n",
-    "        metric_type=\"wer\",\n",
-    "        metric_name=\"WER\",\n",
-    "        dataset_name='indonesian-nlp/librivox-indonesia',\n",
-    "        dataset_type='indonesian-nlp/librivox-indonesia',\n",
-    "        dataset_split='test',\n",
-    "        dataset_config='ind',\n",
-    "        task_type=\"automatic-speech-recognition\",\n",
-    "        task_name=\"Automatic Speech Recognition\",\n",
-    "        overwrite=True\n",
-    "    )\n",
-    "\n",
-    "evaluate.push_to_hub(\n",
-    "        model_id='Scrya/whisper-medium-id',\n",
-    "        metric_value=round(lbv_results['eval_cer'], 2),\n",
-    "        metric_type=\"cer\",\n",
-    "        metric_name=\"CER\",\n",
-    "        dataset_name='indonesian-nlp/librivox-indonesia',\n",
-    "        dataset_type='indonesian-nlp/librivox-indonesia',\n",
-    "        dataset_split='test',\n",
-    "        dataset_config='ind',\n",
+    "        dataset_config='vi',\n",
     "        task_type=\"automatic-speech-recognition\",\n",
     "        task_name=\"Automatic Speech Recognition\",\n",
     "        overwrite=True\n",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a198f73597f974a9b74522823ad7d16370ef807878385efcc5945ee134d380
+oid sha256:04a4c5aa4fd868f15c45ea43819bf1a6d4e1cd9a54087bf4c7e3542040491896
 size 3055754841

runs/Dec18_12-13-24_150-136-94-223/events.out.tfevents.1671365617.150-136-94-223.67469.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e922a9f6d4ea475193b553b08076d621bb11071df57552f74f8ec7d14339c89f
-size 7778
+oid sha256:82e79925d6935ad64abeab6957af5c2421302c5eaabde093f13d112431abb2e2
+size 9034

runs/Dec18_13-16-20_150-136-94-223/1671369384.9831293/events.out.tfevents.1671369384.150-136-94-223.188704.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30bb44e17063d501a2c481a6b2bc2d9942bccf3ec23df2ef39eeae3f60d9ec4e
+size 5864

runs/Dec18_13-16-20_150-136-94-223/events.out.tfevents.1671369384.150-136-94-223.188704.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d5c1e008fca368c38df82e9c94653dc1219462e0d29b6e634a51da2fe160f3
+size 10920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930fc6dc1ee2cc305974e960626c59df89c2d1745ae686b41cc2fc7f12bcf6ed
+oid sha256:f973458f69771b6165ab9524285a6bd70a0e5439fe024937cb09b41b37c8902a
 size 3579