update .md and .ipynb

[divyashreepathihalli]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @divyashreepathihalli, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request implements a focused bug fix to the Transformer model's loss calculation logic within the transformer_asr example. The change ensures that the model correctly references its own compute_loss method during training and evaluation steps, which is crucial for the model's proper functioning and accurate loss reporting. The correction is mirrored in both the executable notebook and its static markdown representation.

Highlights

• Code Correction: I've identified a critical correction in how the compute_loss method is invoked within the Transformer model. Previously, it was incorrectly calling model.compute_loss, implying an external model object, but it has been updated to self.compute_loss, ensuring the model correctly uses its own defined loss computation method.
• Consistency Across Formats: The same compute_loss method call correction has been applied consistently across both the Jupyter Notebook (.ipynb) and its corresponding Markdown (.md) version of the transformer_asr example, maintaining code integrity in both interactive and documentation formats.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request fixes a critical bug by correcting the call to compute_loss within the Transformer model's train_step and test_step methods. The original code incorrectly used model.compute_loss instead of self.compute_loss, which would have caused a NameError.

[gemini-code-assist]

Consider using keyword arguments for clarity when calling compute_loss. This enhances readability and maintainability.

            loss = self.compute_loss(y=one_hot, y_pred=preds, sample_weight=mask)

[gemini-code-assist]

Consider using keyword arguments for clarity when calling compute_loss. This enhances readability and maintainability.

        loss = self.compute_loss(y=one_hot, y_pred=preds, sample_weight=mask)