mudler--localai
wehub-resource-sync
28 行
1.0 KiB
YAML
28 行
1.0 KiB
YAML
---
|
|
name: "sherpa-onnx-asr"
|
|
|
|
config_file: |
|
|
backend: sherpa-onnx
|
|
type: asr
|
|
options:
|
|
# Feature extraction. Most shipped sherpa-onnx ASR models expect
|
|
# 16 kHz / 80-dim log-mel; derivatives trained at other rates
|
|
# should override these.
|
|
- asr.sample_rate=16000
|
|
- asr.feature_dim=80
|
|
- asr.decoding_method=greedy_search
|
|
# Whisper-family defaults (ignored by non-whisper models).
|
|
- asr.whisper.task=transcribe
|
|
- asr.whisper.tail_paddings=-1
|
|
# SenseVoice-family: inverse text normalization is off in upstream
|
|
# sherpa but on here — we want formatted transcription output
|
|
# ("100" not "one hundred"). Set to 0 for raw tokens.
|
|
- asr.sense_voice.use_itn=1
|
|
# Online (streaming zipformer) ASR. Endpoint detection is upstream-
|
|
# off but on here — streaming consumers need segment boundaries.
|
|
- online.enable_endpoint=1
|
|
- online.rule1_min_trailing_silence=2.4
|
|
- online.rule2_min_trailing_silence=1.2
|
|
- online.rule3_min_utterance_length=20.0
|
|
- online.chunk_samples=1600
|