Parakeet text cleanups #1193

zhang-lucy · 2025-05-22T20:10:23Z

Type of Change

New example for the GitHub repo
- New example for the documentation site (Linked from a discoverable page, e.g. via the sidebar in /docs/examples)
Example updates (Bug fixes, new features, etc.)
Other (Changes to the codebase, but not to examples)

Documentation Site Checklist

☑️ Monitoring

Example is configured for testing in the synthetic monitoring system
- Example is tested by executing with modal run, or an alternative cmd is provided in the example frontmatter (e.g. cmd: ["modal", "serve"])
- Example is tested by running the cmd with no arguments, or the args are provided in the example frontmatter (e.g. args: ["--prompt", "Formula for room temperature superconductor:"]
- Example does not require third-party dependencies besides fastapi to be installed locally (e.g. does not import requests or torch in the global scope or other code executed locally)

☑️ Content

Example is documented with comments throughout, in a Literate Programming style
All media assets for the example that are rendered in the documentation site page are retrieved from modal-cdn.com

☑️ Build Stability

Example pins all dependencies in container images
- Example pins container images to a stable tag like v1, not a dynamic tag like latest
- Example specifies a python_version for the base image, if it is used
- Example pins all dependencies to at least SemVer minor version, ~=x.y.z or ==x.y, or we expect this example to work across major versions of the dependency and are committed to maintenance across those versions
  - Example dependencies with version < 1 are pinned to patch version, ==0.y.z

Outside Contributors

You're great! Thanks for your contribution.

charlesfrye · 2025-05-22T20:14:43Z

🚀 The docs preview is ready! Check it out here: https://modal-labs-examples--frontend-preview-bd2d836.modal.run

charlesfrye · 2025-05-22T20:15:38Z

🚀 The docs preview is ready! Check it out here: https://modal-labs-examples--frontend-preview-61c1417.modal.run

charlesfrye · 2025-05-22T20:30:39Z

🚀 The docs preview is ready! Check it out here: https://modal-labs-examples--frontend-preview-d4e954b.modal.run

zhang-lucy · 2025-05-22T20:33:09Z

06_gpu_and_ml/audio-to-text/parakeet.py

@@ -275,9 +278,7 @@ def main(audio_url: str = AUDIO_URL):
 # Below are the three main functions that coordinate streaming audio and receiving transcriptions.
 #
 # `send_audio` transmits chunks of audio data and then pauses to approximate streaming
-# speech at a natural rate. That said, we set it to faster


thought this was a bit too honest 😅

I would say the prose is too casual.

I'll resist defending the tone of this sentence. But it might be worth mentioning that we set it to faster than realtime just so people understand why we divide the wait time by 8 (i.e. wait for 1/8th the duration of the chunk we just sent).

Probably okay to not mention it. it's not crucial or the focus here.

charlesfrye · 2025-05-22T20:34:42Z

🚀 The docs preview is ready! Check it out here: https://modal-labs-examples--frontend-preview-43bff72.modal.run

06_gpu_and_ml/audio-to-text/parakeet.py

charlesfrye · 2025-05-22T20:48:10Z

06_gpu_and_ml/audio-to-text/parakeet.py

 # ...
 # ```
+# See [Troubleshooting](https://modal.com/docs/examples/parakeet#client) at the bottom if you run into issues.


I don't think we need the Troubleshooting section anymore.

charlesfrye · 2025-05-22T20:50:56Z

🚀 The docs preview is ready! Check it out here: https://modal-labs-examples--frontend-preview-694f621.modal.run

shababo

Thanks for taking another pass at this!

shababo · 2025-05-22T20:51:21Z

06_gpu_and_ml/audio-to-text/parakeet.py


-# - run the browser/microphone frontend, or
+# - Run the browser/microphone frontend. Modal handles the deployment of both the frontend and backend in a single app! You should see a browser window pop up - make sure you allow access to your microphone. The full frontend code can be found [here](https://github.com/modal-labs/modal-examples/tree/main/06_gpu_and_ml/audio-to-text/frontend).


Do we need the callout to it being a single app?

For me the browser window does not pop up automatically... I have to click the link in the terminal. Does it automatically open for you?

I always think it's so cool but defer to you guys

Oh good catch; will fix

shababo · 2025-05-22T20:52:40Z

06_gpu_and_ml/audio-to-text/parakeet.py


 # ```bash
 # 🌐 Downloading audio file...
 # 🎧 Downloaded 6331478 bytes
 # ☀️ Waking up model, this may take a few seconds on cold start...
 # 📝 Transcription: A Dream Within A Dream Edgar Allan Poe
 # 📝 Transcription:
-# 📝 Transcription: take this kiss upon the brow, And in parting from you now, Thus much let me avow You are not wrong who deem That my days have been a dream.
+# 📝 Transcription: Take this kiss upon the brow,


It doesn't actually break up the lines like this in the output... do we want it to be the actual output or this better looking one?

I kinda like the better looking one but defer to you guys if that's dishonest 😅

Movie magic yk

@charlesfrye what's the Modal-Frye Style Guide say here?

I think splitting on punctuation with newlines in the code is a good idea! I'd like for the output to be real.

@charlesfrye i feel like coding that is a can of worms. like, just breaking on , or . could have false positives. right now line breaks are based on speech breaks. using a poem as the example is fun but complicates this a bit.

shababo · 2025-05-22T20:55:38Z

06_gpu_and_ml/audio-to-text/parakeet.py

@@ -275,9 +278,7 @@ def main(audio_url: str = AUDIO_URL):
 # Below are the three main functions that coordinate streaming audio and receiving transcriptions.
 #
 # `send_audio` transmits chunks of audio data and then pauses to approximate streaming
-# speech at a natural rate. That said, we set it to faster


I'll resist defending the tone of this sentence. But it might be worth mentioning that we set it to faster than realtime just so people understand why we divide the wait time by 8 (i.e. wait for 1/8th the duration of the chunk we just sent).

charlesfrye · 2025-05-22T20:59:55Z

🚀 The docs preview is ready! Check it out here: https://modal-labs-examples--frontend-preview-b852fe8.modal.run

charlesfrye · 2025-05-27T14:40:18Z

🚀 The docs preview is ready! Check it out here: https://modal-labs-examples--frontend-preview-ed65e78.modal.run

shababo · 2025-05-27T17:23:56Z

06_gpu_and_ml/audio-to-text/parakeet.py

@@ -376,3 +377,27 @@ def preprocess_audio(audio_bytes: bytes) -> bytes:
 def chunk_audio(data: bytes, chunk_size: int):
    for i in range(0, len(data), chunk_size):
        yield data[i : i + chunk_size]
+
+
+def output_message_as_transcript(message: str):


This might be weird. At the very least we shouldn't change the punctuation and just do a word wrap where we limit the number of chars per line. @charlesfrye thoughts on this?

charlesfrye · 2025-05-28T04:17:51Z

🚀 The docs preview is ready! Check it out here: https://modal-labs-examples--frontend-preview-11af6fe.modal.run

charlesfrye · 2025-05-28T04:19:33Z

@prbot automerge

zhang-lucy force-pushed the zhang-lucy/parakeet-cleanup branch from 7788457 to 29b704b Compare May 22, 2025 20:10

zhang-lucy commented May 22, 2025

View reviewed changes

zhang-lucy requested review from charlesfrye and shababo May 22, 2025 20:33

zhang-lucy marked this pull request as ready for review May 22, 2025 20:33

zhang-lucy added 2 commits May 22, 2025 16:33

more text cleanups

f82d881

nits

eabfaf1

zhang-lucy force-pushed the zhang-lucy/parakeet-cleanup branch from 942ceb2 to eabfaf1 Compare May 22, 2025 20:33

charlesfrye reviewed May 22, 2025

View reviewed changes

06_gpu_and_ml/audio-to-text/parakeet.py Outdated Show resolved Hide resolved

charlesfrye reviewed May 22, 2025

View reviewed changes

06_gpu_and_ml/audio-to-text/parakeet.py Outdated Show resolved Hide resolved

minor text changes

7b4724f

charlesfrye reviewed May 22, 2025

View reviewed changes

zhang-lucy changed the title ~~[draft] Parakeet text cleanups~~ Parakeet text cleanups May 22, 2025

rm troubleshooting

cce3bed

shababo reviewed May 22, 2025

View reviewed changes

zhang-lucy requested a review from charlesfrye May 25, 2025 13:50

update

8f13d09

shababo reviewed May 27, 2025

View reviewed changes

charlesfrye added 3 commits May 28, 2025 04:09

minor text fixes and reorganization

e361fe3

silence unnecessary logs

484bd0c

refactor out one level of async nesting

882a0b7

charlesfrye approved these changes May 28, 2025

View reviewed changes

modal-pr-review-automation bot merged commit 1d80e4f into main May 28, 2025
7 checks passed

modal-pr-review-automation bot deleted the zhang-lucy/parakeet-cleanup branch May 28, 2025 04:19


		# - run the browser/microphone frontend, or
		# - Run the browser/microphone frontend. Modal handles the deployment of both the frontend and backend in a single app! You should see a browser window pop up - make sure you allow access to your microphone. The full frontend code can be found [here](https://github.com/modal-labs/modal-examples/tree/main/06_gpu_and_ml/audio-to-text/frontend).

Parakeet text cleanups #1193

Parakeet text cleanups #1193

Uh oh!

Conversation

zhang-lucy commented May 22, 2025

Type of Change

Documentation Site Checklist

☑️ Monitoring

☑️ Content

☑️ Build Stability

Outside Contributors

Uh oh!

charlesfrye commented May 22, 2025

Uh oh!

charlesfrye commented May 22, 2025

Uh oh!

charlesfrye commented May 22, 2025

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

charlesfrye commented May 22, 2025

Uh oh!

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

charlesfrye commented May 22, 2025

Uh oh!

shababo left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

charlesfrye commented May 22, 2025

Uh oh!

charlesfrye commented May 27, 2025

Uh oh!

Choose a reason for hiding this comment

Uh oh!

charlesfrye commented May 28, 2025

Uh oh!

charlesfrye commented May 28, 2025

Uh oh!

Uh oh!

Uh oh!