fixed sampling rate issue on compute_fbank_librispeech.py by Prithwin55 · Pull Request #2060 · k2-fsa/icefall

Prithwin55 · 2026-01-20T09:50:19Z

Fixed sampling rate convertion to 16000 HZ on librispeech fbank computing to match fbank extractors expected sampling rate

Summary by CodeRabbit

Bug Fixes
- Improved audio data preprocessing by ensuring proper sampling rate standardization (16000 Hz) during the initial data preparation stage, enhancing downstream feature extraction and model training reliability.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

… computing to match fbank extractors expected sampling rate

gemini-code-assist · 2026-01-20T09:50:30Z

Summary of Changes

Hello @Prithwin55, 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 addresses a critical sampling rate inconsistency in the Librispeech fbank computation script. By explicitly resampling audio to 16kHz, it guarantees that the feature extraction process receives data in the correct format, thereby ensuring the reliability and accuracy of the generated fbank features for downstream tasks.

Highlights

Sampling Rate Correction: Introduced an explicit audio resampling step to ensure the input audio for fbank computation is consistently at 16000 Hz.
Fbank Extractor Compatibility: The resampling ensures that the audio data matches the expected sampling rate of the fbank extractors, preventing potential mismatches or errors in feature generation.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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.

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. ↩

coderabbitai · 2026-01-20T09:50:34Z

📝 Walkthrough

Walkthrough

Introduces a preprocessing step that resamples audio cuts to 16000 Hz immediately after loading from manifests, before subsequent feature extraction and augmentation operations. This ensures the Fbank extractor receives audio at its expected sampling rate.

Changes

Cohort / File(s)	Summary
Audio preprocessing normalization `egs/librispeech/ASR/local/compute_fbank_librispeech.py`	Added resampling operation to standardize cut_set to 16000 Hz sample rate after manifest loading, ensuring downstream Fbank feature extraction receives correctly formatted audio

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~5 minutes

Poem

🐰 A hop, a resample, sixteen-thousand times,
The audio now matches what Fbank designs,
No more mismatched rates to cause a fuss,
Just clean sixteen kHz flowing through us! 🎵

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately reflects the main change: fixing a sampling rate issue in compute_fbank_librispeech.py by resampling to 16000 Hz.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

📝 Generate docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

gemini-code-assist

Code Review

This pull request fixes an issue with the sampling rate in compute_fbank_librispeech.py by explicitly resampling the audio to 16000 Hz to match the Fbank extractor's expectation. The change is correct and addresses the problem described. My feedback includes a suggestion to replace the hardcoded sampling rate with a constant to improve code quality and maintainability.

gemini-code-assist · 2026-01-20T09:51:31Z

egs/librispeech/ASR/local/compute_fbank_librispeech.py

+            logging.info(f"Resampling audio to 16000 Hz")
+            cut_set = cut_set.resample(16000)


The sampling rate 16000 is used as a magic number in both the log message and the resample call. It's a good practice to define such values as constants to improve code readability and maintainability. This makes it easier to find and change the value if needed in the future.

For example:

SAMPLING_RATE = 16000 logging.info(f"Resampling audio to {SAMPLING_RATE} Hz") cut_set = cut_set.resample(SAMPLING_RATE)

Ideally, this constant would be defined at a broader scope (e.g., at the top of the function) and also used when creating the Fbank extractor on line 119 to ensure consistency.

coderabbitai

Actionable comments posted: 1

🤖 Fix all issues with AI agents

In `@egs/librispeech/ASR/local/compute_fbank_librispeech.py`:
- Line 134: The logging call using an unnecessary f-string should be changed to
a normal string literal: update the logging.info call in
compute_fbank_librispeech.py (the line that currently reads
logging.info(f"Resampling audio to 16000 Hz")) to remove the leading "f" so it
becomes logging.info("Resampling audio to 16000 Hz"); this eliminates the unused
f-string prefix and resolves the F541 lint warning while keeping the same log
message.

coderabbitai · 2026-01-20T09:54:15Z

egs/librispeech/ASR/local/compute_fbank_librispeech.py

            )
+
+            # Resample audio to 16kHz to match Fbank extractor's expected sampling rate
+            logging.info(f"Resampling audio to 16000 Hz")


⚠️ Potential issue | 🟡 Minor

Drop the unused f-string prefix.

This log line has no placeholders, so the f prefix is redundant and triggers F541.

🔧 Proposed fix

- logging.info(f"Resampling audio to 16000 Hz") + logging.info("Resampling audio to 16000 Hz")

📝 Committable suggestion

‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.

Suggested change

logging.info(f"Resampling audio to 16000 Hz")

logging.info("Resampling audio to 16000 Hz")

🧰 Tools

🪛 Ruff (0.14.13)

134-134: f-string without any placeholders

Remove extraneous f prefix

(F541)

🤖 Prompt for AI Agents

In `@egs/librispeech/ASR/local/compute_fbank_librispeech.py` at line 134, The logging call using an unnecessary f-string should be changed to a normal string literal: update the logging.info call in compute_fbank_librispeech.py (the line that currently reads logging.info(f"Resampling audio to 16000 Hz")) to remove the leading "f" so it becomes logging.info("Resampling audio to 16000 Hz"); this eliminates the unused f-string prefix and resolves the F541 lint warning while keeping the same log message.

csukuangfj · 2026-01-20T10:03:32Z

egs/librispeech/ASR/local/compute_fbank_librispeech.py

+
+            # Resample audio to 16kHz to match Fbank extractor's expected sampling rate
+            logging.info(f"Resampling audio to 16000 Hz")
+            cut_set = cut_set.resample(16000)


Can you explain which error this is fixing?

AssertionError: Fbank was instantiated for sampling_rate 16000, but sampling_rate=8000 was passed to extract().

There was mismatch in the sampling rate when some audios are not recorded in 16000 Hz

Is it your own data?

All data from librispeech has a sample rate 16000 Hz.

well i was using a custom dataset!

[fix] Fixed sampling rate convertion to 16000 HZ on librispeech fbank…

69f4a5b

… computing to match fbank extractors expected sampling rate

gemini-code-assist bot reviewed Jan 20, 2026

View reviewed changes

coderabbitai bot reviewed Jan 20, 2026

View reviewed changes

csukuangfj reviewed Jan 20, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

fixed sampling rate issue on compute_fbank_librispeech.py#2060

fixed sampling rate issue on compute_fbank_librispeech.py#2060
Prithwin55 wants to merge 1 commit intok2-fsa:masterfrom
Prithwin55:fix/sampling

Prithwin55 commented Jan 20, 2026 •

edited by coderabbitai bot

Loading

Uh oh!

gemini-code-assist bot commented Jan 20, 2026

Uh oh!

coderabbitai bot commented Jan 20, 2026 •

edited

Loading

Walkthrough

Changes

Estimated code review effort

Poem

Uh oh!

gemini-code-assist bot left a comment

Uh oh!

gemini-code-assist bot Jan 20, 2026

Uh oh!

coderabbitai bot left a comment

Uh oh!

coderabbitai bot Jan 20, 2026

Uh oh!

csukuangfj Jan 20, 2026

Uh oh!

Prithwin55 Jan 20, 2026

Uh oh!

csukuangfj Jan 20, 2026

Uh oh!

Prithwin55 Jan 20, 2026 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

		logging.info(f"Resampling audio to 16000 Hz")
		cut_set = cut_set.resample(16000)

	logging.info(f"Resampling audio to 16000 Hz")
	logging.info("Resampling audio to 16000 Hz")

Conversation

Prithwin55 commented Jan 20, 2026 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

gemini-code-assist bot commented Jan 20, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

coderabbitai bot commented Jan 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Poem

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Jan 20, 2026

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

coderabbitai bot Jan 20, 2026

Choose a reason for hiding this comment

Uh oh!

csukuangfj Jan 20, 2026

Choose a reason for hiding this comment

Uh oh!

Prithwin55 Jan 20, 2026

Choose a reason for hiding this comment

Uh oh!

csukuangfj Jan 20, 2026

Choose a reason for hiding this comment

Uh oh!

Prithwin55 Jan 20, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Prithwin55 commented Jan 20, 2026 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Jan 20, 2026 •

edited

Loading

Prithwin55 Jan 20, 2026 •

edited

Loading