"
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ " | \n",
+ " sentence | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " бөмбөгөө хураалгахаас зайлсхийн зүгээр л ойролцоох тоглогч руу чиглүүлээд чулуудаж орхив | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " цайзад бидний түүсэн мөчир байгаа гэж эд хариулав | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " гидролизын урвалыг ашиглан хамгийн хурдан үйлчилдэг уургийн хэлбэрийг гарган авчээ | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " энэ төсвийг жаалуудаас харамлаж жалга довны зүйлд зарлагадсан гэж хардахаас өөр арга алга | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " санал хүсэлтийн утсыг олон газар ажиллуулдаг ч залгаад улам уурлаад дуусах нь элбэг тохиолддог | \n",
+ "
\n",
+ " \n",
+ " | 5 | \n",
+ " байшингийн захиргааны дарга энэ ярианд сэтгэл огт ханасангүй | \n",
+ "
\n",
+ " \n",
+ " | 6 | \n",
+ " аливаа зүйл хомсдохдоо ү��э цэн нь өсөж хүмүүс түүнийг улам ихээр үгүйлдэг | \n",
+ "
\n",
+ " \n",
+ " | 7 | \n",
+ " харин дархан джузеппег тэр аль хэдийнээс мэддэг байлаа | \n",
+ "
\n",
+ " \n",
+ " | 8 | \n",
+ " марияд эх орноо хайрлах үзэл нялх бага байхад нь л төлөвшсөн | \n",
+ "
\n",
+ " \n",
+ " | 9 | \n",
+ " тэгээд гэнэт цочин ээжийг харахад дуугүйхэн нулимсаа арчиж байна | \n",
+ "
\n",
+ " \n",
+ "
"
+ ]
+ },
+ "metadata": {}
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "def extract_all_chars(batch):\n",
+ " all_text = \" \".join(batch[\"sentence\"])\n",
+ " vocab = list(set(all_text))\n",
+ " return {\"vocab\": [vocab], \"all_text\": [all_text]}"
+ ],
+ "metadata": {
+ "id": "bfcwBKamNDX8"
+ },
+ "execution_count": 15,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "vocab_train = common_voice_train.map(extract_all_chars, batched=True, batch_size=-1, keep_in_memory=True, remove_columns=common_voice_train.column_names)\n",
+ "vocab_test = common_voice_test.map(extract_all_chars, batched=True, batch_size=-1, keep_in_memory=True, remove_columns=common_voice_test.column_names)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 81,
+ "referenced_widgets": [
+ "22a73456734c4195a8b664eea56060b4",
+ "a6fb84966d464fb084e4ff28fb819597",
+ "759972fc0c264e7ca12c3e9beefb687b",
+ "c0de6ce1aecf4f9b9f55cc0fb3dd408b",
+ "14634a3546bb4d05ac892a8e236b388c",
+ "4b498b14406545c1bed99f25a6594722",
+ "69f722871117402fa549647da50e76d7",
+ "e9f0076bedaf46eba7c84f22f3c3a516",
+ "e79476d487e844c1ae3ba3ac3c6b8a92",
+ "cc98af514295460ebfde23cd3ab74588",
+ "974993c7e39647ba93a6af05513c8911",
+ "d26ded21d3d040c78d51a0b366aade4e",
+ "46e7918fe0f947a9bd1579875dd1e709",
+ "d25e569e8bdf4130b57cbd4a8f73396a",
+ "e962a75632054a6991d235f3404cebbf",
+ "adf9836a19b34730a49b75748678d4e4",
+ "aacf7a1900ee4b049f742e5d71641653",
+ "01e1f849ead44c1c99fa749d62dc5be8",
+ "d5ab34c153ed4649ae42e8fcce7779c6",
+ "1a547a8d2a964a3a93f307036d58b45d",
+ "1f3b5f5f73274fc498ff04f73cd45033",
+ "42c73ab5ffb84f04b848f4479cc2cb25"
+ ]
+ },
+ "id": "_Lz5XcXMWlRK",
+ "outputId": "0c20cd73-f955-4d15-c00a-0aeca25cbb69"
+ },
+ "execution_count": 16,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ " 0%| | 0/1 [00:00 Dict[str, torch.Tensor]:\n",
+ " # split inputs and labels since they have to be of different lenghts and need\n",
+ " # different padding methods\n",
+ " input_features = [{\"input_values\": feature[\"input_values\"]} for feature in features]\n",
+ " label_features = [{\"input_ids\": feature[\"labels\"]} for feature in features]\n",
+ "\n",
+ " batch = self.processor.pad(\n",
+ " input_features,\n",
+ " padding=self.padding,\n",
+ " return_tensors=\"pt\",\n",
+ " )\n",
+ " with self.processor.as_target_processor():\n",
+ " labels_batch = self.processor.pad(\n",
+ " label_features,\n",
+ " padding=self.padding,\n",
+ " return_tensors=\"pt\",\n",
+ " )\n",
+ "\n",
+ " # replace padding with -100 to ignore loss correctly\n",
+ " labels = labels_batch[\"input_ids\"].masked_fill(labels_batch.attention_mask.ne(1), -100)\n",
+ "\n",
+ " batch[\"labels\"] = labels\n",
+ "\n",
+ " return batch"
+ ],
+ "metadata": {
+ "id": "whu0EJxOgfyy"
+ },
+ "execution_count": 36,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "data_collator = DataCollatorCTCWithPadding(processor=processor, padding=True)"
+ ],
+ "metadata": {
+ "id": "Ltc2dxGlgukN"
+ },
+ "execution_count": 37,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from datasets import load_dataset, load_metric, Audio"
+ ],
+ "metadata": {
+ "id": "QS5WEKd8hnhi"
+ },
+ "execution_count": 38,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "wer_metric = load_metric(\"wer\")"
+ ],
+ "metadata": {
+ "id": "xR73S4hhglX_",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 49,
+ "referenced_widgets": [
+ "97b0443dfc314fcaa1f58148e7b0fe51",
+ "11618b57382943e4a308591cfad2e9e5",
+ "9a62654284a04fcdac75d5dfbab9eca5",
+ "8747480e6ddb4831b538d0b0b69b77a6",
+ "ff19a949944f48ad8a06589868ff5f1e",
+ "e5bab6c722a54f79b63b489ad87a1e8f",
+ "935ed8c2c69044979a4f4fa51b3c60c9",
+ "d4bc82f10abc4a2a9fc7ebb810c4a233",
+ "6f1886c3a50a40acb8b50d3a40782f51",
+ "ffdb0fd1ce574c64bb3e351e33e3c89b",
+ "e7b0c2f4568e4214ac4e6202eee9a8cc"
+ ]
+ },
+ "outputId": "378cdcc0-5339-4478-dd1e-247d2f6ab410"
+ },
+ "execution_count": 39,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ "Downloading: 0%| | 0.00/1.90k [00:00"
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ "
\n",
+ " [1800/1800 2:21:35, Epoch 30/30]\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | Step | \n",
+ " Training Loss | \n",
+ " Validation Loss | \n",
+ " Wer | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 400 | \n",
+ " 2.249400 | \n",
+ " 0.848729 | \n",
+ " 0.526894 | \n",
+ "
\n",
+ " \n",
+ " | 800 | \n",
+ " 0.143000 | \n",
+ " 0.829556 | \n",
+ " 0.525183 | \n",
+ "
\n",
+ " \n",
+ " | 1200 | \n",
+ " 0.100700 | \n",
+ " 0.813215 | \n",
+ " 0.504110 | \n",
+ "
\n",
+ " \n",
+ " | 1600 | \n",
+ " 0.070000 | \n",
+ " 0.833226 | \n",
+ " 0.480113 | \n",
+ "
\n",
+ " \n",
+ "
"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.\n",
+ "***** Running Evaluation *****\n",
+ " Num examples = 1862\n",
+ " Batch size = 8\n",
+ "Saving model checkpoint to repo_name/checkpoint-400\n",
+ "Configuration saved in repo_name/checkpoint-400/config.json\n",
+ "Model weights saved in repo_name/checkpoint-400/pytorch_model.bin\n",
+ "Configuration saved in repo_name/checkpoint-400/preprocessor_config.json\n",
+ "/usr/local/lib/python3.9/dist-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",
+ "The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.\n",
+ "***** Running Evaluation *****\n",
+ " Num examples = 1862\n",
+ " Batch size = 8\n",
+ "Saving model checkpoint to repo_name/checkpoint-800\n",
+ "Configuration saved in repo_name/checkpoint-800/config.json\n",
+ "Model weights saved in repo_name/checkpoint-800/pytorch_model.bin\n",
+ "Configuration saved in repo_name/checkpoint-800/preprocessor_config.json\n",
+ "/usr/local/lib/python3.9/dist-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",
+ "The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.\n",
+ "***** Running Evaluation *****\n",
+ " Num examples = 1862\n",
+ " Batch size = 8\n",
+ "Saving model checkpoint to repo_name/checkpoint-1200\n",
+ "Configuration saved in repo_name/checkpoint-1200/config.json\n",
+ "Model weights saved in repo_name/checkpoint-1200/pytorch_model.bin\n",
+ "Configuration saved in repo_name/checkpoint-1200/preprocessor_config.json\n",
+ "Deleting older checkpoint [repo_name/checkpoint-400] due to args.save_total_limit\n",
+ "/usr/local/lib/python3.9/dist-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",
+ "The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.\n",
+ "***** Running Evaluation *****\n",
+ " Num examples = 1862\n",
+ " Batch size = 8\n",
+ "Saving model checkpoint to repo_name/checkpoint-1600\n",
+ "Configuration saved in repo_name/checkpoint-1600/config.json\n",
+ "Model weights saved in repo_name/checkpoint-1600/pytorch_model.bin\n",
+ "Configuration saved in repo_name/checkpoint-1600/preprocessor_config.json\n",
+ "Deleting older checkpoint [repo_name/checkpoint-800] due to args.save_total_limit\n",
+ "/usr/local/lib/python3.9/dist-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",
+ "\n",
+ "\n",
+ "Training completed. Do not forget to share your model on huggingface.co/models =)\n",
+ "\n",
+ "\n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "TrainOutput(global_step=1800, training_loss=0.5758350520663791, metrics={'train_runtime': 8501.5757, 'train_samples_per_second': 6.772, 'train_steps_per_second': 0.212, 'total_flos': 7.124680585822395e+18, 'train_loss': 0.5758350520663791, 'epoch': 30.0})"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 44
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "common_voice_test_transcription = load_dataset(\"common_voice\", \"mn\", data_dir=\"./cv-corpus-6.1-2020-12-11\", split=\"test\")\n",
+ "\n",
+ "for i in range(10):\n",
+ " input_dict = processor(common_voice_test[i][\"input_values\"], return_tensors=\"pt\", padding=True)\n",
+ "\n",
+ " logits = model(input_dict.input_values.to(\"cuda\")).logits\n",
+ "\n",
+ " pred_ids = torch.argmax(logits, dim=-1)[0]\n",
+ "\n",
+ " print(f\"Prediction_{i}:\")\n",
+ " print(processor.decode(pred_ids))\n",
+ "\n",
+ " print(f\"\\nReference_{i}:\")\n",
+ " print(common_voice_test_transcription[i][\"sentence\"].lower())"
+ ],
+ "metadata": {
+ "id": "FHIIY-qT7qo4",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "bdfdcb9d-01f5-4816-c9c7-7ca328805c82"
+ },
+ "execution_count": 54,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "WARNING:datasets.builder:Using custom data configuration mn-00b7e43d66b8c1a3\n",
+ "WARNING:datasets.builder:Reusing dataset common_voice (/root/.cache/huggingface/datasets/common_voice/mn-00b7e43d66b8c1a3/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd)\n",
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n",
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Prediction_0:\n",
+ "хэрэв захиа байгаагүй бол чиг андалсын тухай дурсах ч үгүй байсан\n",
+ "\n",
+ "Reference_0:\n",
+ "хэрэв захиа байгаагүй бол чи гэндальфын тухай дурсах ч үгүй байсан.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Prediction_1:\n",
+ "алтагууны ширээн дээр мэдээдллэг харагдахуулц байрнь цоог дөшүүлөн тавьжээ\n",
+ "\n",
+ "Reference_1:\n",
+ "гал тогооны ширээн дээр мэдээллийг харагдахуйц байранд сав түшүүлэн тавьжээ.\n",
+ "Prediction_2:\n",
+ "энэ мо та хоёр яг адилхань бага болчир шүү дээ\n",
+ "\n",
+ "Reference_2:\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n",
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "энэ мод та хоёр яг адилхан бага балчир шүү дээ.\n",
+ "Prediction_3:\n",
+ "чойллсон ч тэгж бодсон нь бий\n",
+ "\n",
+ "Reference_3:\n",
+ "чойбалсан ч тэгж бодсон нь бий.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Prediction_4:\n",
+ "мөн л овоог нэгэн насриг нь тодорхойсон өнгө бүрийн туузүй зүүжээ\n",
+ "\n",
+ "Reference_4:\n",
+ "мөн л овог нэр насыг нь тодорхойлсон өнгө бүрийн тууз зүүжээ.\n",
+ "Prediction_5:\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n",
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "үнэндээ гэхэд би нэ бутын хаань ч хаяг бүртгэлгүй явна шүү дээ\n",
+ "\n",
+ "Reference_5:\n",
+ "үнэндээ гэхэд би энэ хотын хаана нь ч хаяг бүртгэлгүй явна шүү дээ.\n",
+ "Prediction_6:\n",
+ "сайн ч мөрдөгч бас шилдэг дарга байсан юм шүү\n",
+ "\n",
+ "Reference_6:\n",
+ "сайн ч мөрдөгч бас шилдэг дарга байсан юм шүү.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Prediction_7:\n",
+ "эцэг эхчүүд сурагчид та бүхэн доорхаягаар урж захим хичээлэн хийгээрэй\n",
+ "\n",
+ "Reference_7:\n",
+ "эцэг, эхчүүд, сурагчид та бүхэн доорх хаягаар орж цахим хичээлээ хийгээрэй.\n",
+ "Prediction_8:\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "It is strongly recommended to pass the ``sampling_rate`` argument to this function.Failing to do so can result in silent errors that might be hard to debug.\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "та шинэ жэлийн баяраар илүү чамин баярын уур амьсгал оруулах гоёмсог умьс бэлллээтээ\n",
+ "\n",
+ "Reference_8:\n",
+ "та шинэ жилийн баяраар илүү чамин баярын уур амьсгал оруулах гоёмсог оймс бэлэглээрэй.\n",
+ "Prediction_9:\n",
+ "машины тунслогуйн тагарвал яана сайхан хувцаа баллай л гэсэн үг\n",
+ "\n",
+ "Reference_9:\n",
+ "машины донсолгоонд хагарвал яана, сайхан хувцсаа баллана л гэсэн үг.\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Даалгавар 1\n",
+ "энэхүү сургалтын WER 48% бууруулах\n",
+ "\n",
+ "# Даалгавар 2\n",
+ "өөрийн яриаг сургалтанд ашиглах\n",
+ "\n",
+ "# Даалгавар 3\n",
+ "Бусад сүүлийн үеийн модел ашиглан сургах\n",
+ "\n",
+ "# Хугацаа 4 долоо хоног"
+ ],
+ "metadata": {
+ "id": "0baGGHnPA7QC"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [],
+ "metadata": {
+ "id": "1r0Xt6q4BvHb"
+ },
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file