fasr-lid-firered 0.5.2

FireRedLID language identification model for fasr

fasr-lid-firered

Chinese documentation

FireRedLID language identification for fasr. It accepts a Waveform and returns a language tag such as "zh" or "en".

Install

pip install fasr-lid-firered

Registered Model

Registry name	Class	Best for
firered	FireRedForLID	Audio language identification with FireRedLID

The default checkpoint is FireRedTeam/FireRedLID.

Direct Model Usage

from fasr.config import registry
from fasr.data import Waveform

model = registry.lid_models.get("firered")(
    use_gpu=True,
    use_half=True,
    max_chunk_seconds=60.0,
)

waveform = Waveform.from_file("example.wav")
language = model.identify(waveform)
print(language)

Use local weights:

model.load_checkpoint("/path/to/FireRedLID")

Confection Config

[lid_model]
@lid_models = "firered"
use_gpu = true
use_half = false
max_chunk_seconds = 60.0

Parameters

Parameter	Type / range	Default	Higher / true	Lower / false	Change when
use_gpu	bool	True	Uses CUDA when available	Uses CPU	You want predictable CPU deployment or faster GPU inference
use_half	bool	False	Uses FP16 on GPU, lower VRAM	Uses FP32, more stable	GPU memory is tight, or FP16 causes instability
max_chunk_seconds	float > 0	60.0	Fewer chunks, more memory per call	More chunks, less memory per call	Long audio causes OOM, or throughput needs tuning

Generic checkpoint fields such as checkpoint, cache_dir, endpoint, revision, and force_download are inherited from the base model.

Tuning Guide

Symptom	Try first
GPU out of memory on long audio	Lower max_chunk_seconds to 20.0 or 30.0
GPU memory is tight	Set use_half=True
CPU-only deployment	Set use_gpu=False
Language result is unstable on very long audio	Keep chunking enabled and aggregate over multiple chunks, the model already votes internally

Dependencies

• fasr
• torch >= 2.0.0
• numpy >= 1.24
• kaldiio >= 2.18.0
• kaldi-native-fbank >= 1.19.0
• Python 3.10-3.12