Dev1nW-webAI commited on
Commit
3d1c475
·
verified ·
1 Parent(s): cf65639

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -26,7 +26,7 @@ it loads in Gradium's unmodified `ptts` runtime on CPU. In a pre-registered test
26
  speech was **as intelligible as the BF16 model's** (word error rate within 0.5 points) and **closer to BF16's audio
27
  than Gradium's Q4_K file**. It also scored higher predicted quality than that file.
28
 
29
- > **Non-commercial use only**. Released under the webAI Non-Commercial License ver. 1.0 (research and education).
30
 
31
  ### At a glance
32
 
@@ -267,10 +267,10 @@ tts.save("speech.wav", "Hello from Echo-Air.", voice="Easton")
267
  step; latent error = mean squared difference of the predicted normalised latents; stop frame = first frame whose
268
  end-of-speech logit exceeds 4.0.
269
 
270
- ## License and attribution
271
-
272
- Released under the webAI Non-Commercial License ver. 1.0 (LICENSE.md). This distribution incorporates a modified version of Gradium’s gradium/phonon-31m-en. Gradium’s weights, tokenizer and voices are licensed under Apache 2.0 (text kept in apache-2.0-LICENSE.txt) and its runtime is licensed under MIT OR Apache-2.0. Please follow Gradium’s model card for its responsible use guidance. No Gradium sponsorship, affiliation, or endorsement is implied.
273
-
274
  ## Responsible Use
275
 
276
  Do not use Echo Air to impersonate a real person, to deceive listeners about who is speaking, or to clone a voice without the speaker’s consent. Tell listeners when speech is synthetic where that matters to them.
 
 
 
 
 
26
  speech was **as intelligible as the BF16 model's** (word error rate within 0.5 points) and **closer to BF16's audio
27
  than Gradium's Q4_K file**. It also scored higher predicted quality than that file.
28
 
29
+ > **Non-commercial use only. Released under the webAI Non-Commercial License ver. 1.0**.
30
 
31
  ### At a glance
32
 
 
267
  step; latent error = mean squared difference of the predicted normalised latents; stop frame = first frame whose
268
  end-of-speech logit exceeds 4.0.
269
 
 
 
 
 
270
  ## Responsible Use
271
 
272
  Do not use Echo Air to impersonate a real person, to deceive listeners about who is speaking, or to clone a voice without the speaker’s consent. Tell listeners when speech is synthetic where that matters to them.
273
+
274
+ ## License and attribution
275
+
276
+ Released under the webAI Non-Commercial License ver. 1.0 (LICENSE.md). This distribution incorporates a modified version of Gradium’s gradium/phonon-31m-en. Gradium’s weights, tokenizer and voices are licensed under Apache 2.0 (text kept in apache-2.0-LICENSE.txt) and its runtime is licensed under MIT OR Apache-2.0. Please follow Gradium’s model card for its responsible use guidance. No Gradium sponsorship, affiliation, or endorsement is implied.