app with requirements and voice samples

app.py

@@ -13,15 +13,16 @@ from transformer_infer import PhemeClient, parse_arguments
 # TODO
 VOICE_OPTIONS = [
         "male_voice",
-        "POD1000000004_S0000246",
-        "POD1000000018_S0000253",
-        "POD1000000048_S0000035",
-        "YOU1000000006_S0000051",
-        "YOU1000000044_S0000798",
-        "empress",
+        "POD1000000004_S0000246", 
+        "POD1000000018_S0000253", 
+        "POD1000000048_S0000035", 
+        "YOU1000000006_S0000051", 
+        "YOU1000000044_S0000798", 
+        "empress", 
 ]
 
 args = parse_arguments()
+
 model = PhemeClient(args)
 
 
@@ -73,4 +74,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

demo/audios-speech-tokenizer/acoustic/POD0000004393_S0000029.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e39339fa61656c27b20c8acf300781489916ff2c213dc7a1ce933deb29240258
+size 21072

demo/audios-speech-tokenizer/acoustic/POD0000007005_S0000568.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc9f301051e0523e80b73d481b19e8fe37ac05501ea1cb1dbdd218485ea19e7f
+size 22304

demo/audios-speech-tokenizer/acoustic/POD0000009720_S0000244.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b447cdd6a4040ee249c796ea6b65d9edda683c610a85824837ea3d29b4d076b
+size 14632

demo/audios-speech-tokenizer/acoustic/POD0000014360_S0000082.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a55b1d85b858fe110b6bf108b1e624465da10a2b988df70ded55cdabb6a884b
+size 18440

demo/audios-speech-tokenizer/acoustic/POD0000015908_S0000037.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfd99a497a3835cead58c86c3d27dd5783dbcd72836b0a63bf7498cf8207fb8
+size 18888

demo/audios-speech-tokenizer/acoustic/POD1000000004_S0000246.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e8dc99b392561ae96f5aa33b5614c28f2e64891e2888c563e3c5c4dd260576a
+size 34176

demo/audios-speech-tokenizer/acoustic/POD1000000018_S0000253.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3b443aee90059efe52c5733dd85d03e57380aa9bd1ae59f8cf3dcbf4accc8e
+size 36080

demo/audios-speech-tokenizer/acoustic/POD1000000022_S0000028.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92787aaadb7503ac127f1a3f560bfdeee2751bd7b351ad21e1ce5daeadf09fc5
+size 17152

demo/audios-speech-tokenizer/acoustic/POD1000000048_S0000035.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b533fe4d8d4a7cd95a2a0e3e493cc4d778863e992c8d32c913df15bd547083
+size 38768

demo/audios-speech-tokenizer/acoustic/YOU1000000006_S0000051.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee97e27fabbd3dbb0f2c56ba8f71f7e0b21294b74dd448d1e4606fa2c61e310e
+size 24208

demo/audios-speech-tokenizer/acoustic/YOU1000000044_S0000798.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35bad4b7c8a3f103a9d56fe77861d521b16559f4f5e4fed73e6391073a64699
+size 19000

demo/audios-speech-tokenizer/acoustic/empress.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca403a4a0826a4f5a10bdaa5f3fa1a8d2ef2c5b2dfd227054a2eb9770bbd603
+size 13736

demo/audios-speech-tokenizer/acoustic/male_voice.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58d9ce7c7952855af4e485c600ff2dd1f887339d261d63fbf5a72beb658c189
+size 17432

demo/audios-speech-tokenizer/semantic/POD0000004393_S0000029.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e2828236bc9f7341035e1355ed2fe1aaff32a30fa7123d0478be674dd669ec
+size 3120

demo/audios-speech-tokenizer/semantic/POD0000007005_S0000568.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5a61301691cad79a2f8f1d27616384dc3e8a024d68c4a4a22c397a6cc8c804
+size 3296

demo/audios-speech-tokenizer/semantic/POD0000009720_S0000244.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9d483b7741a8c9200cf21a3c647120eb571c799add53fdc763b172ef3ab940
+size 2200

demo/audios-speech-tokenizer/semantic/POD0000014360_S0000082.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ed5c809906790eb7765d168d6ba23bd4c06dfac0e02a01651c6c84c473f830
+size 2744

demo/audios-speech-tokenizer/semantic/POD0000015908_S0000037.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ec64462c0be2613ec7b5c2e5db406612ed512c4097feb83114c204dd83e748
+size 2808

demo/audios-speech-tokenizer/semantic/POD1000000004_S0000246.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace66c2fa29263462b52f479d77dba3a1cc9e4a090c50aa6623ddc5cd592b925
+size 4992

demo/audios-speech-tokenizer/semantic/POD1000000018_S0000253.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2a3fa5b262edba5c61865404ea381afa4921f436c5e039589febf630fdf5e2
+size 5264

demo/audios-speech-tokenizer/semantic/POD1000000022_S0000028.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e9da7813c7cc6ddea55a2d2f8141febed9acd9b3043fd61f7b99834e8909d9
+size 2560

demo/audios-speech-tokenizer/semantic/POD1000000048_S0000035.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deece6ebc3c0270ec874ae397700305ef807b0a8cb493a6b6d0b7c162ec7b065
+size 5648

demo/audios-speech-tokenizer/semantic/YOU1000000006_S0000051.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f155557ceb5177680001b675ac60745cbab50a74327bfc03801a7f63c068bbc
+size 3568

demo/audios-speech-tokenizer/semantic/YOU1000000044_S0000798.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed39bb7580f5b9adc1f12fee2f8af470aca4a172c739b34897de9cb7bceac66a
+size 2824

demo/audios-speech-tokenizer/semantic/empress.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ec65c6f0ccb1d2c84fb35571459d509d0c63f89fa124b219408a14af2aa060
+size 2072

demo/audios-speech-tokenizer/semantic/male_voice.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10482039872004d398fb2c87dc4f09bd92bc4afca783b0857c4bc30eba4fdb68
+size 2600

demo/manifest.json

@@ -0,0 +1,7 @@
+{"audio_filepath":"male_voice.wav","text":"Welcome to Casino Lakes Charles. I'm very happy to help you today. We have a broad range of goods for you!","speaker":0,"audio_prompt_filepath":"audios/male_voice.wav"}
+{"audio_filepath":"POD1000000004_S0000246.wav","text":"in early twenty-twenty, blue apron put the word out that it was interested in possibly getting scooped up. maybe by a big grocery chain. or someone else with deep pockets who wanted to own a meal kit delivery business.","speaker":0,"audio_prompt_filepath":"audios/POD1000000004_S0000246.wav"}
+{"audio_filepath":"POD1000000018_S0000253.wav","text":"aside from influencing basically everyone who matters he was one of the first if not, in fact the first artist to bring an electric guitar player with him on to the grand ole opry stage.","speaker":0,"audio_prompt_filepath":"audios/POD1000000018_S0000253.wav"}
+{"audio_filepath":"POD1000000048_S0000035.wav","text":"so it's ah i think there's a range of risks, but generally speaking ah there's going to be a study increase in the floor of the skill level as these ah a i technologies diffuse.","speaker":0,"audio_prompt_filepath":"audios/POD1000000048_S0000035.wav"}
+{"audio_filepath":"YOU1000000006_S0000051.wav","text":"so after they put in their name, phone number, email address onto your landing page. where would you like to send them? would you like to send them to your facebook page your website?","speaker":0,"audio_prompt_filepath":"audios/YOU1000000006_S0000051.wav"}
+{"audio_filepath":"YOU1000000044_S0000798.wav","text":"let's just say in her own words, once i sat down and watched it i never moved, i was enthralled by it.","speaker":0,"audio_prompt_filepath":"audios/YOU1000000044_S0000798.wav"}
+{"audio_filepath":"empress","text":"Our hotel’s rooftop garden yoga sessions are both calming and invigorating.","speaker":0,"audio_prompt_filepath":"audios/empress.wav"}

requirements.txt

@@ -0,0 +1 @@
+https://github.com/PolyAI-LDN/pheme#egg=pheme