Conversation
…mosv2 for mean opinion score estimation. Small dataset pathway bug adjustments.
pcsid
requested review from
akshaykalkunte,
nhhoang96,
oluwanifemibamgbose and
shruthan
pcsid
changed the title
jonggunp
reviewed
Apr 22, 2026
|
|
||
| # URL is only required for non-TTS inference types | ||
| inference_type = info.get('inference_type') | ||
| if inference_type not in ['cartesia_tts', 'elevenlabs_tts', 'deepgram_tts']: |
Collaborator
There was a problem hiding this comment.
not a big deal, but should we be using constants instead?
jonggunp
reviewed
Apr 22, 2026
| raise ValueError(f"Model {index}: '{field}' must be a non-empty string") | ||
|
|
||
| # Require voice_id for TTS inference types | ||
| if inference_type in ['cartesia_tts', 'elevenlabs_tts']: |
Collaborator
There was a problem hiding this comment.
do we need deepgram here?
jonggunp
reviewed
Apr 22, 2026
| for i, audio_file in enumerate(batch_files): | ||
| temp_name = f"audio_{i:06d}.wav" | ||
| temp_path = os.path.join(temp_dir, temp_name) | ||
| shutil.copy(audio_file, temp_path) |
Collaborator
There was a problem hiding this comment.
audio_paths in tts_postprocessor.py can be an empty string. This will cause "audio_file" to be an empty string.
You may need to address line 109 so that it only shutil.copies when audio_file exists
jonggunp
reviewed
Apr 22, 2026
|
|
||
| Args: | ||
| message: Input message containing ground_truth_text | ||
| run_params: Runtime parameters for the inference request |
Collaborator
There was a problem hiding this comment.
this is never used in this method.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
…mosv2 for mean opinion score estimation. Small dataset pathway bug adjustments.
📌 Description
This feature was to added to support text to speech evaluations for AU-Harness. Cartesia, Deepgram, and ElevenLabs clients are supported.
Also made some bug fixes to the dataset paths in the ASR task.
🛠️ Type of Change
✅ How Has This Been Tested?
Test Results / Screenshots (if applicable):
📸 Screenshots / Demos
📋 Checklist
🙌 Additional Notes