STT/ASR - onnx
Collection
OVOS STT/ASR models for onnx-asr (ONNX runtime). Most ship fp32 + int8 (set quantization: int8 for faster/smaller CPU inference). • 234 items • Updated • 2
stt-tl-fastconformer-hybrid-large-onnx
ASR model exported to ONNX for the onnx-asr library and the ovos-stt-plugin-onnx-asr OpenVoiceOS STT plugin. Ships both the RNNT head (default) and the CTC head.
Language: Tagalog / Filipino. Converted from NCSpeech/stt_tl_fastconformer_hybrid_large, a FastConformer Hybrid Transducer+CTC model (EncDecHybridRNNTCTCBPEModel).
Reported WER (source model card): 9.34% on FLEURS (fil_ph), 16.1% on Magic Data Tech (Tagalog).
Usage
onnx-asr
import onnx_asr
model = onnx_asr.load_model("OpenVoiceOS/stt-tl-fastconformer-hybrid-large-onnx")
print(model.recognize("audio.wav"))
ovos-stt-plugin-onnx-asr
stt:
module: ovos-stt-plugin-onnx-asr
ovos-stt-plugin-onnx-asr:
model: OpenVoiceOS/stt-tl-fastconformer-hybrid-large-onnx
lang: tl
Credits
Original model by NCSpeech, released under the CC-BY-4.0 license: NCSpeech/stt_tl_fastconformer_hybrid_large.
- Downloads last month
- 105
Model tree for OpenVoiceOS/stt-tl-fastconformer-hybrid-large-onnx
Base model
NCSpeech/stt_tl_fastconformer_hybrid_large