whatmodel.sh / tts / Amphion VALL-E (LibriLight 6k)
Amphion VALL-E (LibriLight 6k)
↗ share
+ contribute
Amphion VALL-E (LibriLight 6k) is an open-weights text-to-speech model from Amphion (CUHK-Shenzhen), released January 2024. Licence: mit.
Catalogue identity notes
amphion/valle_librilight_6k: Amphion's open reproduction of VALL-E (v1 recipe) trained on 6k hours of Libri-Light. Microsoft's original VALL-E was never released.
Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.
$ how it compares
The text-to-speech models ranked either side of Amphion VALL-E (LibriLight 6k), out of 148 with a score, then more from Amphion (CUHK-Shenzhen).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 93 |  Kyutai TTS 1.6B en/fr | 47±5 | local | ||
| 94 |  MiMo v2.5 TTS | 47±4 | comparison only | ||
| 95 | Amphion VALL-E (LibriLight 6k) | 47±14 | local | ||
| 96 |  Piper (en_US lessac medium) | 47±5 | local | ||
| 97 | Vevo (Amphion) | 46±3 | local | ||
| more from Amphion (CUHK-Shenzhen) | |||||
| 53 | MaskGCT | 59±1 | local | ||
| 121 | Amphion VALL-E v2 recipe (MLS) | 36±3 | local | ||
| 146 | Amphion NaturalSpeech 2 (LibriTTS) | 14±3 | local | ||
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests1 not in a task · 17% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| TTSDS v1 · default four-factor score | 83.7% ✎ | ▂▂····▃·▃▅▂█ beats 4/14 | 17% |
$ where to run it
Other ways to run it
- Run it as published · needs ~1.56 GB, NVIDIA only · from huggingface.co/amphion (official)
git lfs install && git clone https://huggingface.co/amphion/valle_librilight_6k && git clone https://github.com/open-mmlab/Amphion.git && cd Amphion && conda create --name amphion python=3.9.15 && conda activate amphion && sh env.sh && mkdir -p ckpts/tts && ln -s ../../../valle_librilight_6k ckpts/tts/ && sh egs/tts/VALLE/run.sh --stage 3 --gpu "0" --config "ckpts/tts/valle_librilight_6k/args.json" --infer_expt_dir ckpts/tts/valle_librilight_6k --infer_output_dir ckpts/tts/valle_librilight_6k/result --infer_mode "single" --infer_text "This is a clip of generated speech with the given text from Amphion Vall-E model." --infer_text_prompt "But even the unsuccessful dramatist has his moments." --infer_audio_prompt egs/tts/VALLE/prompt_examples/7176_92135_000004_000000.wav
Official weights and documentation: huggingface.co/amphion ↗
$ how the score was worked out · TTSDS v1 published results 17%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 TTSDS v1 published results | 1 | 17% |
| prior · pull toward the middle | 83% | |
| weighted average | = 46.6 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json