diff --git a/audio/tts_samples/p1995_1837_000020_000000/1995_1836_000003_000002_16k.wav b/audio/tts_samples/p1995_1837_000020_000000/1995_1836_000003_000002_16k.wav new file mode 100644 index 0000000..7e9d1d7 Binary files /dev/null and b/audio/tts_samples/p1995_1837_000020_000000/1995_1836_000003_000002_16k.wav differ diff --git a/audio/tts_samples/p1995_1837_000020_000000/lauraGPT_p1995_1837_000020_000000.wav b/audio/tts_samples/p1995_1837_000020_000000/lauraGPT_p1995_1837_000020_000000.wav new file mode 100644 index 0000000..349871c Binary files /dev/null and b/audio/tts_samples/p1995_1837_000020_000000/lauraGPT_p1995_1837_000020_000000.wav differ diff --git a/audio/tts_samples/p1995_1837_000020_000000/prompt_p1995_1837_000020_000000.wav b/audio/tts_samples/p1995_1837_000020_000000/prompt_p1995_1837_000020_000000.wav new file mode 100644 index 0000000..27628b5 Binary files /dev/null and b/audio/tts_samples/p1995_1837_000020_000000/prompt_p1995_1837_000020_000000.wav differ diff --git a/audio/tts_samples/p1995_1837_000020_000000/valle_phn_p1995_1837_000020_000000.wav b/audio/tts_samples/p1995_1837_000020_000000/valle_phn_p1995_1837_000020_000000.wav new file mode 100644 index 0000000..52060ba Binary files /dev/null and b/audio/tts_samples/p1995_1837_000020_000000/valle_phn_p1995_1837_000020_000000.wav differ diff --git a/audio/tts_samples/p1995_1837_000020_000000/valle_token_p1995_1837_000020_000000.wav b/audio/tts_samples/p1995_1837_000020_000000/valle_token_p1995_1837_000020_000000.wav new file mode 100644 index 0000000..3107647 Binary files /dev/null and b/audio/tts_samples/p1995_1837_000020_000000/valle_token_p1995_1837_000020_000000.wav differ diff --git a/audio/tts_samples/p2830_3980_000018_000001/2830_3980_000018_000000_16k.wav b/audio/tts_samples/p2830_3980_000018_000001/2830_3980_000018_000000_16k.wav new file mode 100644 index 0000000..b38d049 Binary files /dev/null and b/audio/tts_samples/p2830_3980_000018_000001/2830_3980_000018_000000_16k.wav differ diff --git a/audio/tts_samples/p2830_3980_000018_000001/lauraGPT_p2830_3980_000018_000001.wav b/audio/tts_samples/p2830_3980_000018_000001/lauraGPT_p2830_3980_000018_000001.wav new file mode 100644 index 0000000..5b81c4f Binary files /dev/null and b/audio/tts_samples/p2830_3980_000018_000001/lauraGPT_p2830_3980_000018_000001.wav differ diff --git a/audio/tts_samples/p2830_3980_000018_000001/prompt_p2830_3980_000018_000001.wav b/audio/tts_samples/p2830_3980_000018_000001/prompt_p2830_3980_000018_000001.wav new file mode 100644 index 0000000..b94a21c Binary files /dev/null and b/audio/tts_samples/p2830_3980_000018_000001/prompt_p2830_3980_000018_000001.wav differ diff --git a/audio/tts_samples/p2830_3980_000018_000001/valle_phn_p2830_3980_000018_000001.wav b/audio/tts_samples/p2830_3980_000018_000001/valle_phn_p2830_3980_000018_000001.wav new file mode 100644 index 0000000..f1ffe34 Binary files /dev/null and b/audio/tts_samples/p2830_3980_000018_000001/valle_phn_p2830_3980_000018_000001.wav differ diff --git a/audio/tts_samples/p2830_3980_000018_000001/valle_token_p2830_3980_000018_000001.wav b/audio/tts_samples/p2830_3980_000018_000001/valle_token_p2830_3980_000018_000001.wav new file mode 100644 index 0000000..b196c7a Binary files /dev/null and b/audio/tts_samples/p2830_3980_000018_000001/valle_token_p2830_3980_000018_000001.wav differ diff --git a/audio/tts_samples/p6829_68771_000046_000000/6829_68769_000030_000000_16k.wav b/audio/tts_samples/p6829_68771_000046_000000/6829_68769_000030_000000_16k.wav new file mode 100644 index 0000000..13157f3 Binary files /dev/null and b/audio/tts_samples/p6829_68771_000046_000000/6829_68769_000030_000000_16k.wav differ diff --git a/audio/tts_samples/p6829_68771_000046_000000/lauraGPT_p6829_68771_000046_000000.wav b/audio/tts_samples/p6829_68771_000046_000000/lauraGPT_p6829_68771_000046_000000.wav new file mode 100644 index 0000000..2b1a73e Binary files /dev/null and b/audio/tts_samples/p6829_68771_000046_000000/lauraGPT_p6829_68771_000046_000000.wav differ diff --git a/audio/tts_samples/p6829_68771_000046_000000/prompt_p6829_68771_000046_000000.wav b/audio/tts_samples/p6829_68771_000046_000000/prompt_p6829_68771_000046_000000.wav new file mode 100644 index 0000000..9118523 Binary files /dev/null and b/audio/tts_samples/p6829_68771_000046_000000/prompt_p6829_68771_000046_000000.wav differ diff --git a/audio/tts_samples/p6829_68771_000046_000000/valle_phn_p6829_68771_000046_000000.wav b/audio/tts_samples/p6829_68771_000046_000000/valle_phn_p6829_68771_000046_000000.wav new file mode 100644 index 0000000..1560f9c Binary files /dev/null and b/audio/tts_samples/p6829_68771_000046_000000/valle_phn_p6829_68771_000046_000000.wav differ diff --git a/audio/tts_samples/p6829_68771_000046_000000/valle_token_p6829_68771_000046_000000.wav b/audio/tts_samples/p6829_68771_000046_000000/valle_token_p6829_68771_000046_000000.wav new file mode 100644 index 0000000..e48a07e Binary files /dev/null and b/audio/tts_samples/p6829_68771_000046_000000/valle_token_p6829_68771_000046_000000.wav differ diff --git a/audio/tts_samples/p8230_279154_000004_000008/8230_279154_000019_000000_16k.wav b/audio/tts_samples/p8230_279154_000004_000008/8230_279154_000019_000000_16k.wav new file mode 100644 index 0000000..b734a86 Binary files /dev/null and b/audio/tts_samples/p8230_279154_000004_000008/8230_279154_000019_000000_16k.wav differ diff --git a/audio/tts_samples/p8230_279154_000004_000008/lauraGPT_p8230_279154_000004_000008.wav b/audio/tts_samples/p8230_279154_000004_000008/lauraGPT_p8230_279154_000004_000008.wav new file mode 100644 index 0000000..e16dad6 Binary files /dev/null and b/audio/tts_samples/p8230_279154_000004_000008/lauraGPT_p8230_279154_000004_000008.wav differ diff --git a/audio/tts_samples/p8230_279154_000004_000008/prompt_p8230_279154_000004_000008.wav b/audio/tts_samples/p8230_279154_000004_000008/prompt_p8230_279154_000004_000008.wav new file mode 100644 index 0000000..9219e38 Binary files /dev/null and b/audio/tts_samples/p8230_279154_000004_000008/prompt_p8230_279154_000004_000008.wav differ diff --git a/audio/tts_samples/p8230_279154_000004_000008/valle_phn_p8230_279154_000004_000008.wav b/audio/tts_samples/p8230_279154_000004_000008/valle_phn_p8230_279154_000004_000008.wav new file mode 100644 index 0000000..15f5b84 Binary files /dev/null and b/audio/tts_samples/p8230_279154_000004_000008/valle_phn_p8230_279154_000004_000008.wav differ diff --git a/audio/tts_samples/p8230_279154_000004_000008/valle_token_p8230_279154_000004_000008.wav b/audio/tts_samples/p8230_279154_000004_000008/valle_token_p8230_279154_000004_000008.wav new file mode 100644 index 0000000..b12f290 Binary files /dev/null and b/audio/tts_samples/p8230_279154_000004_000008/valle_token_p8230_279154_000004_000008.wav differ diff --git a/index.html b/index.html index 4da09e1..c0de4f8 100644 --- a/index.html +++ b/index.html @@ -328,39 +328,197 @@

1. Automatic speech recognition (ASR) samples

- - - - - - - - - - - - - - - - - - - - - - - - - - - - +

2. Text-to-speech synthesis (TTS) samples

+
+
[Prompt: 1995_1837_000020_000000] Up in the sick room Zora lay on the little white bed. [Continuation: 1995_1836_000003_000002] At last the Cotton Combine was to all appearances an assured fact and he was slated for the Senate.
+
+ + + + + + + + + + + + + + - - - + + + + + + + + +
+
Prompt wav (16k)Ground-truth (16k)VALLE-PhoneVALLE-TokenLauraGPT
+ + + + + + + + + +
+
[Prompt: 2830_3980_000018_000001] Humble man that he was, he will not now take a back seat. [Continuation: 2830_3980_000018_000000] Against these boasting, false apostles, Paul boldly defends his apostolic authority and ministry.
+ + + + + + + + + + + + + + + + + + + + + + + + +
+
Prompt wav (16k)Ground-truth (16k)VALLE-PhoneVALLE-TokenLauraGPT
+ + + + + + + + + +
+
[Prompt: 6829_68771_000046_000000] A sudden wave of scarlet swept over Eliza's face. [Continuation: 6829_68769_000030_000000] Then he deliberately locked Kenneth and Beth in with the forger, and retreated along the passage.
+ + + + + + + + + + + + + + + + + + + + + + + + +
+
Prompt wav (16k)Ground-truth (16k)VALLE-PhoneVALLE-TokenLauraGPT
+ + + + + + + + + +
+
[Prompt: 8230_279154_000004_000008] To deal with this problem, we must have a theory of memory. [Continuation: 8230_279154_000019_000000] The first of our vague but indubitable data is that there is knowledge of the past.
+ + + + + + + + + + + + + + + + + + + + + + + + +
Prompt wav (16k)Ground-truth (16k)VALLE-PhoneVALLE-TokenLauraGPT
+ + + + + + + + + +
+

3. Speech to text translation (S2TT) samples