Amphion
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
Runs with mockssource: GitHubhomepagePythonMITcommit 26f688311018
Python, MIT licensed. The project labels itself: audio generation, audio synthesis, audioldm, audit, emilia, fastspeech2, maskgct and music generation.
Amphion runs, with stand-ins for the services it depends on. An Argusic agent installed it in 18 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Core dependencies installed, evaluation metrics compute correctly on audio pairs, model classes import cleanly. pyworld-dependent f0 metrics unavailable without python3-dev headers. Cython monotonic_align extension uncompiled for same reason.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pyworld, pysptk, pesq, webrtcvad failed to build from source: missing python3-dev (Python.h header). No root access to install it.4 minutes
- Multiple missing __init__.py files in modules/ subdirectories (modules/base, modules/diffusion/bidilconv, modules/diffusion/karras, modules/diffusion/unet, modules/flow, modules/naturalpseech2, modules/wenet_extractor/*)1 minute
- fairseq missing version.txt - failed pip install from git1 minute
- librosa 0.9.1 requires pkg_resources from setuptools; newer setuptools broke it1 minute
- lhotse not installed (required by modules/general)1 minute
- transformers 5.x missing soxr dependency for Wav2Vec21 minute
- Install time
- 18 minutes
- Cold machine to finish
- 25 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- python -c computed evaluation metrics (MSTFT=0.136, SI-SDR=19.97, SI-SNR=19.97, V/UV F1=0.0) on synthetic audio pairs using extract_mstft, extract_si_sdr, extract_si_snr. Core model imports (FastSpeech2, HiFiGAN, MelGAN, BigVGAN) and module imports (encoder, transformer, norms, general, vocoder_blocks) all succeed. Python module imports exercised without errors.
- Model tokens used
- 535,343
- Exact commit tested
- 26f688311018
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/work/repo/evaluation/metrics/f0/v_uv_f1.py:98: UserWarning: Creating a tensor from a list of numpy…
ref_voiced = torch.Tensor([f0_ref != 0]).bool()
{
"mstft": 0.13607480935752392,
"si_sdr": 19.970428466796875,
"si_snr": 19.970428466796875,
"v_uv_f1": 0.0
}
Now I have a comprehensive picture. Here's the full report:
tokens used
535,343
Now I have a comprehensive picture. Here's the full report:Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 18 minutes.
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.14 |
Topics (from GitHub)
audio-generationaudio-synthesisaudioldmauditemiliafastspeech2maskgctmusic-generationnaturalspeech2singing-voice-conversionspeech-synthesistext-to-audiotext-to-speechvall-evitsvocodervoice-conversion
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/amphion)Questions
- Does Amphion run?
- Amphion runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 18 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test Amphion?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 26f688311018. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Amphion?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Amphion take to install?
- 18 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does Amphion need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Amphion?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for Amphion?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.