Unverified50% confidenceFactExact time
SteerTTS edge's vocoder is a 6.2M-parameter Vocos-style model distilled from charactr/vocos-mel-24khz and subjected to int4 QAT.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSteerTTS-edge's vocoder is a 6.2-million-parameter Vocos-style model distilled from charactr/vocos-mel-24khz, also using int4 QAT.89% similarUnverifiedSteerTTS edge's acoustic model has 9.25M parameters, uses an attention + bidirectional Mamba-3 architecture, and is compressed to int4 through quantization-aware training (QAT).72% similarUnverifiedSteerTTS adopts FastPitch-style explicit variance modeling: phonemes first pass through an encoder, three predictors for duration, pitch and energy each output control quantities, which are then aligned via a length regulator and finally decoded into 100-band log-mel spectra, handed to a frozen Vocos vocoder for waveform synthesis.71% similarUnverifiedSteerTTS-edge's acoustic model is a 9.25-million-parameter attention + bidirectional Mamba-3 architecture, compressed to int4 precision through quantization-aware training (QAT).64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1087449API
curl https://kongchang.com/api/v1/knowledge/claims/1087449MCP
get_claim(id=1087449)