aethercompute/aether0-500m-muon-bf16-topk8
Text Generation • 0.5B • Updated
alkinun
AtAndDev
AI & ML interests
LLMs, Alignment, Merging, Unsloth, DPO, SFT, ORPO, SPIN..
Recent Activity
updated a model about 6 hours ago
aethercompute/aether0-500m-muon-bf16-topk8 published a model about 6 hours ago
aethercompute/aether0-500m-muon-bf16-topk8 updated a model about 6 hours ago
aethercompute/aether0-500m-muon-bf16-topk6-wd001Organizations
updated a
model about 6 hours ago
published a
model about 6 hours ago
updated a
model about 6 hours ago
published a
model about 6 hours ago
updated a
model about 6 hours ago
published a
model about 6 hours ago
updated a
model about 8 hours ago
published a
model about 8 hours ago
updated a
model about 8 hours ago
published a
model about 8 hours ago
reacted to aufklarer's post with 🔥 1 day ago
Post
1251
Voice cloning models measured across five languages: OmniVoice, Chatterbox, VoxCPM2, Fish Audio
I published a new Soniqo benchmark post for local voice cloning models across five languages:
https://www.soniqo.audio/blog/voice-cloning-benchmarks
Models:
- OmniVoice int8
- Chatterbox Multilingual fp16
- VoxCPM2 bf16
- Fish Audio S2 Pro fp16
Languages:
- English
- German
- Modern Standard Arabic
- Spanish
- Mandarin Chinese
The benchmark uses Google FLEURS test clips as dataset references. Each row includes the reference audio, generated audio, speaker similarity, WER/CER, generated audio length, and RTF.
Main result in this run: OmniVoice was the strongest all-around row set, with 0.707 mean speaker cosine across all five languages, 0.0% ASR error, and mean RTF 0.45. VoxCPM2 bf16 was especially strong on Arabic speaker match. Fish Audio S2 Pro showed strong German/Arabic similarity but slower RTF. Chatterbox Multilingual was competitive on Arabic and Spanish.
This is an engineering benchmark, not a human MOS study. The speaker-similarity values should be compared within this table because every row uses the same local speaker-embedding pipeline.
Try the stack locally with Speech Studio:
https://www.soniqo.audio/speech-studio
https://github.com/soniqo/speech-studio
Underlying Swift library/CLI:
https://github.com/soniqo/speech-swift
Soniqo models and exports:
soniqo @aufklarer
What model or language should I add next?
I published a new Soniqo benchmark post for local voice cloning models across five languages:
https://www.soniqo.audio/blog/voice-cloning-benchmarks
Models:
- OmniVoice int8
- Chatterbox Multilingual fp16
- VoxCPM2 bf16
- Fish Audio S2 Pro fp16
Languages:
- English
- German
- Modern Standard Arabic
- Spanish
- Mandarin Chinese
The benchmark uses Google FLEURS test clips as dataset references. Each row includes the reference audio, generated audio, speaker similarity, WER/CER, generated audio length, and RTF.
Main result in this run: OmniVoice was the strongest all-around row set, with 0.707 mean speaker cosine across all five languages, 0.0% ASR error, and mean RTF 0.45. VoxCPM2 bf16 was especially strong on Arabic speaker match. Fish Audio S2 Pro showed strong German/Arabic similarity but slower RTF. Chatterbox Multilingual was competitive on Arabic and Spanish.
This is an engineering benchmark, not a human MOS study. The speaker-similarity values should be compared within this table because every row uses the same local speaker-embedding pipeline.
Try the stack locally with Speech Studio:
https://www.soniqo.audio/speech-studio
https://github.com/soniqo/speech-studio
Underlying Swift library/CLI:
https://github.com/soniqo/speech-swift
Soniqo models and exports:
What model or language should I add next?
Coding tuned model
❤️ 2
4
#18 opened 8 days ago
by 
almirneeto99
liked 2
models 2 days ago
liked a
dataset 2 days ago
liked 2
models 2 days ago