Skip to content

Integrate ChunkFormer-RNNT to API for inferene #22

@khanld

Description

@khanld

UPDATE:

Feel free to test and report issues:


#23
Issue: Currently, ChunkFormer-RNNT decoding is not supported in the package
Expected:

from chunkformer import ChunkFormerModel

# Load a pre-trained model from Hugging Face or local directory
model = ChunkFormerModel.from_pretrained("khanhld/chunkformer-rnnt-large-vie")

# For single long-form audio transcription
transcription = model.endless_decode(
    audio_path="path/to/long_audio.wav",
    chunk_size=64,
    left_context_size=128,
    right_context_size=128,
    total_batch_duration=14400,  # in seconds
    return_timestamps=True
)
print(transcription)

Metadata

Metadata

Assignees

Labels

featureNew feature or requesthighhigh priority

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions