Skip to content

Navigation Menu

Appearance settings

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

huggingface / smolagents Public

Notifications You must be signed in to change notification settings
Fork 1.9k
Star 21.7k

Code
Issues 159
Pull requests 110
Discussions
Actions
Projects 1
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Security
Insights

Fix: SpeechToTextTool returns incoherent transcripts#1480

Open

Martin-Labenne wants to merge 6 commits intohuggingface:mainhuggingface/smolagents:mainfrom

Martin-Labenne:fix/1478-stt-transcript-and-logsMartin-Labenne/smolagents:fix/1478-stt-transcript-and-logsCopy head branch name to clipboard

Conversation Commits6 (6)Checks Files changed

Open

Fix: SpeechToTextTool returns incoherent transcripts#1480
Martin-Labenne wants to merge 6 commits intohuggingface:mainfrom
Martin-Labenne:fix/1478-stt-transcript-and-logs

Commits

Commits on Jun 24, 2025

fix(stt): Pass sampling_rate to WhisperFeatureExtractor to avoid silent errors
Martin-Labenne
committed
fix(stt): Set attention_mask to ensure reliable model behavior
Martin-Labenne
committed
fix(stt): allow explicit language setting via forced_decoder_ids
Martin-Labenne
committed
fix(stt): improve transcript quality via audio resampling
Martin-Labenne
committed
fix(stt): add support for long audio inputs (more than 30s)
Martin-Labenne
committed
fix(audio): move resample logic to AgentAudio to pass tool validation
Martin-Labenne
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.