{
  "id": 450502,
  "title": "81st Place Solution for Bengali.Ai Speech Recognition.",
  "url": "/competitions/bengaliai-speech/discussion/450502",
  "author_name": "Yash Goel",
  "post_date": "2023-10-24T15:29:18.855000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<h2>1. Fine Tuning Wev2Vec2:</h2>\n<p>Training Notebook: <a href=\"https://www.kaggle.com/code/takanashihumbert/bengali-sr-wav2vec-v1-bengali-training\" target=\"_blank\">https://www.kaggle.com/code/takanashihumbert/bengali-sr-wav2vec-v1-bengali-training</a></p>\n<p>Dataset Used: <a href=\"https://www.kaggle.com/datasets/umongsain/common-voice-13-bengali-normalized\" target=\"_blank\">https://www.kaggle.com/datasets/umongsain/common-voice-13-bengali-normalized</a></p>\n<p>Hyperparameters:</p>\n<p>LR: 1 e-4<br>\nEpochs: 15<br>\nLogging step: 5000</p>\n<h2>2. Use Optuna to find the Best decoding Parameters.</h2>\n<p>Notebook: <a href=\"https://www.kaggle.com/code/royalacecat/lb-0-442-the-best-decoding-parameters\" target=\"_blank\">https://www.kaggle.com/code/royalacecat/lb-0-442-the-best-decoding-parameters</a></p>\n<p>best_params = {'alpha': 0.3802723523729998, 'beta': 0.053996879617918436, 'beam_width': 1024}</p>\n<h2>Score:</h2>\n<table>\n<thead>\n<tr>\n<th>public</th>\n<th>private</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>0.432</td>\n<td>0.518</td>\n</tr>\n<tr>\n<td>0.435</td>\n<td>0.518</td>\n</tr>\n</tbody>\n</table>",
  "messages": [
    {
      "id": 2497356,
      "postDate": "2023-10-24T15:29:18.857Z",
      "content": "<h2>1. Fine Tuning Wev2Vec2:</h2>\n<p>Training Notebook: <a href=\"https://www.kaggle.com/code/takanashihumbert/bengali-sr-wav2vec-v1-bengali-training\" target=\"_blank\">https://www.kaggle.com/code/takanashihumbert/bengali-sr-wav2vec-v1-bengali-training</a></p>\n<p>Dataset Used: <a href=\"https://www.kaggle.com/datasets/umongsain/common-voice-13-bengali-normalized\" target=\"_blank\">https://www.kaggle.com/datasets/umongsain/common-voice-13-bengali-normalized</a></p>\n<p>Hyperparameters:</p>\n<p>LR: 1 e-4<br>\nEpochs: 15<br>\nLogging step: 5000</p>\n<h2>2. Use Optuna to find the Best decoding Parameters.</h2>\n<p>Notebook: <a href=\"https://www.kaggle.com/code/royalacecat/lb-0-442-the-best-decoding-parameters\" target=\"_blank\">https://www.kaggle.com/code/royalacecat/lb-0-442-the-best-decoding-parameters</a></p>\n<p>best_params = {'alpha': 0.3802723523729998, 'beta': 0.053996879617918436, 'beam_width': 1024}</p>\n<h2>Score:</h2>\n<table>\n<thead>\n<tr>\n<th>public</th>\n<th>private</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>0.432</td>\n<td>0.518</td>\n</tr>\n<tr>\n<td>0.435</td>\n<td>0.518</td>\n</tr>\n</tbody>\n</table>",
      "rawMarkdown": "## 1. Fine Tuning Wev2Vec2: \n\nTraining Notebook: https://www.kaggle.com/code/takanashihumbert/bengali-sr-wav2vec-v1-bengali-training\n\nDataset Used: https://www.kaggle.com/datasets/umongsain/common-voice-13-bengali-normalized\n\nHyperparameters:\n\nLR: 1 e-4\nEpochs: 15\nLogging step: 5000\n\n## 2. Use Optuna to find the Best decoding Parameters.\n\nNotebook: https://www.kaggle.com/code/royalacecat/lb-0-442-the-best-decoding-parameters\n\nbest_params = {'alpha': 0.3802723523729998, 'beta': 0.053996879617918436, 'beam_width': 1024}\n\n## Score:\n\n| public |private  |\n| --- | --- |\n|  0.432| 0.518|\n|0.435|0.518|\n\n\n\n",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2497356": "## 1. Fine Tuning Wev2Vec2: \n\nTraining Notebook: https://www.kaggle.com/code/takanashihumbert/bengali-sr-wav2vec-v1-bengali-training\n\nDataset Used: https://www.kaggle.com/datasets/umongsain/common-voice-13-bengali-normalized\n\nHyperparameters:\n\nLR: 1 e-4\nEpochs: 15\nLogging step: 5000\n\n## 2. Use Optuna to find the Best decoding Parameters.\n\nNotebook: https://www.kaggle.com/code/royalacecat/lb-0-442-the-best-decoding-parameters\n\nbest_params = {'alpha': 0.3802723523729998, 'beta': 0.053996879617918436, 'beam_width': 1024}\n\n## Score:\n\n| public |private  |\n| --- | --- |\n|  0.432| 0.518|\n|0.435|0.518|\n\n\n\n"
  }
}