← Back to API reference

neuralset.extractors.audio.SeamlessM4T

pydantic model neuralset.extractors.audio.SeamlessM4T

Extract speech embeddings using the pretrained Seamless M4T model from Hugging Face.

Seamless M4T is a multilingual, multimodal transformer that includes a dedicated speech encoder. It converts raw audio waveforms into high-level embeddings suitable for speech understanding, translation, and other downstream tasks.

model_name

The Hugging Face model identifier to load. Defaults to "facebook/hf-seamless-m4t-medium".

Type:

str

Fields:

• model_name (str)

field model_name: str = 'facebook/hf-seamless-m4t-medium'

requirements: tp.ClassVar[tuple[str, ...]] = ('transformers>=4.29.2', 'huggingface_hub>=0.27.0', 'julius>=0.2.7', 'pillow>=9.2.0', 'transformers>=4.29.2', 'huggingface_hub>=0.27.0', 'julius>=0.2.7', 'pillow>=9.2.0', 'transformers>=4.29.2', 'soundfile', 'transformers>=4.29.2', 'huggingface_hub>=0.27.0', 'julius>=0.2.7', 'pillow>=9.2.0', 'transformers>=4.29.2', 'huggingface_hub>=0.27.0', 'julius>=0.2.7', 'pillow>=9.2.0', 'transformers>=4.29.2', 'soundfile', 'soundfile')

← Back to API reference