Hugging Face's logo

Spaces:
MERaLiON
/
MERaLiON-AudioLLM
Running

App Files Community
YingxuHe commited on
Commit
8573823
·
0 Parent(s):

update demo

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +35 -0
  2. .streamlit/config.toml +2 -0
  3. README.md +14 -0
  4. app.py +3 -0
  5. audio_samples/10_ASR_IMDA_PART4_30_ASR_v2_1527.wav +0 -0
  6. audio_samples/11_ASR_IMDA_PART4_30_ASR_v2_3771.wav +0 -0
  7. audio_samples/12_ASR_IMDA_PART4_30_ASR_v2_103.wav +0 -0
  8. audio_samples/13_ASR_IMDA_PART5_30_ASR_v2_1446.wav +0 -0
  9. audio_samples/14_ASR_IMDA_PART5_30_ASR_v2_2281.wav +0 -0
  10. audio_samples/15_ASR_IMDA_PART5_30_ASR_v2_4388.wav +0 -0
  11. audio_samples/16_ASR_IMDA_PART6_30_ASR_v2_576.wav +0 -0
  12. audio_samples/17_ASR_IMDA_PART6_30_ASR_v2_1413.wav +0 -0
  13. audio_samples/18_ASR_IMDA_PART6_30_ASR_v2_2834.wav +0 -0
  14. audio_samples/19_ASR_AIShell_zh_ASR_v2_5044.wav +0 -0
  15. audio_samples/1_ASR_IMDA_PART1_ASR_v2_141.wav +0 -0
  16. audio_samples/20_ASR_LIBRISPEECH_CLEAN_ASR_V2_833.wav +0 -0
  17. audio_samples/25_ST_COVOST2_ZH-CN_EN_ST_V2_4567.wav +0 -0
  18. audio_samples/26_ST_COVOST2_EN_ZH-CN_ST_V2_5422.wav +0 -0
  19. audio_samples/27_ST_COVOST2_EN_ZH-CN_ST_V2_6697.wav +0 -0
  20. audio_samples/28_SI_ALPACA-GPT4-AUDIO_SI_V2_299.wav +0 -0
  21. audio_samples/29_SI_ALPACA-GPT4-AUDIO_SI_V2_750.wav +0 -0
  22. audio_samples/2_ASR_IMDA_PART1_ASR_v2_2258.wav +0 -0
  23. audio_samples/30_SI_ALPACA-GPT4-AUDIO_SI_V2_1454.wav +0 -0
  24. audio_samples/31_SI_OPENHERMES-AUDIO_SI_V2_673.wav +0 -0
  25. audio_samples/32_SQA_CN_COLLEDGE_ENTRANCE_ENGLISH_TEST_SQA_V2_572.wav +0 -0
  26. audio_samples/33_SQA_IMDA_PART3_30_SQA_V2_2310.wav +0 -0
  27. audio_samples/34_SQA_IMDA_PART3_30_SQA_V2_3621.wav +0 -0
  28. audio_samples/35_SQA_IMDA_PART3_30_SQA_V2_4062.wav +0 -0
  29. audio_samples/36_DS_IMDA_PART4_30_DS_V2_849.wav +0 -0
  30. audio_samples/39_Paralingual_IEMOCAP_ER_V2_91.wav +0 -0
  31. audio_samples/3_ASR_IMDA_PART1_ASR_v2_2265.wav +0 -0
  32. audio_samples/40_Paralingual_IEMOCAP_ER_V2_567.wav +0 -0
  33. audio_samples/42_Paralingual_IEMOCAP_GR_V2_320.wav +0 -0
  34. audio_samples/43_Paralingual_IEMOCAP_GR_V2_129.wav +0 -0
  35. audio_samples/45_Paralingual_IMDA_PART3_30_GR_V2_12312.wav +0 -0
  36. audio_samples/47_Paralingual_IMDA_PART3_30_NR_V2_10479.wav +0 -0
  37. audio_samples/49_Paralingual_MELD_ER_V2_676.wav +0 -0
  38. audio_samples/4_ASR_IMDA_PART2_ASR_v2_999.wav +0 -0
  39. audio_samples/50_Paralingual_MELD_ER_V2_692.wav +0 -0
  40. audio_samples/51_Paralingual_VOXCELEB1_GR_V2_2148.wav +0 -0
  41. audio_samples/53_Paralingual_VOXCELEB1_NR_V2_2286.wav +0 -0
  42. audio_samples/55_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_2.wav +0 -0
  43. audio_samples/56_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_415.wav +0 -0
  44. audio_samples/57_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_460.wav +0 -0
  45. audio_samples/5_ASR_IMDA_PART2_ASR_v2_2241.wav +0 -0
  46. audio_samples/6_ASR_IMDA_PART2_ASR_v2_3409.wav +0 -0
  47. audio_samples/7_ASR_IMDA_PART3_30_ASR_v2_2269.wav +0 -0
  48. audio_samples/8_ASR_IMDA_PART3_30_ASR_v2_1698.wav +0 -0
  49. audio_samples/9_ASR_IMDA_PART3_30_ASR_v2_2474.wav +0 -0
  50. pages/agent.py +3 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
.streamlit/config.toml ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ [client]
2
+ showSidebarNavigation = false
README.md ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Interactive-Demo / MERaLiON-AudioLLM
3
+ emoji: 🚀
4
+ colorFrom: indigo
5
+ colorTo: indigo
6
+ sdk: streamlit
7
+ sdk_version: 1.41.1
8
+ app_file: app.py
9
+ pinned: true
10
+ models:
11
+ - MERaLiON/MERaLiON-AudioLLM-Whisper-SEA-LION
12
+ ---
13
+
14
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ from src.content.playground import playground_page
2
+
3
+ playground_page()
audio_samples/10_ASR_IMDA_PART4_30_ASR_v2_1527.wav ADDED
Binary file (866 kB). View file
 
audio_samples/11_ASR_IMDA_PART4_30_ASR_v2_3771.wav ADDED
Binary file (642 kB). View file
 
audio_samples/12_ASR_IMDA_PART4_30_ASR_v2_103.wav ADDED
Binary file (565 kB). View file
 
audio_samples/13_ASR_IMDA_PART5_30_ASR_v2_1446.wav ADDED
Binary file (822 kB). View file
 
audio_samples/14_ASR_IMDA_PART5_30_ASR_v2_2281.wav ADDED
Binary file (931 kB). View file
 
audio_samples/15_ASR_IMDA_PART5_30_ASR_v2_4388.wav ADDED
Binary file (947 kB). View file
 
audio_samples/16_ASR_IMDA_PART6_30_ASR_v2_576.wav ADDED
Binary file (750 kB). View file
 
audio_samples/17_ASR_IMDA_PART6_30_ASR_v2_1413.wav ADDED
Binary file (915 kB). View file
 
audio_samples/18_ASR_IMDA_PART6_30_ASR_v2_2834.wav ADDED
Binary file (882 kB). View file
 
audio_samples/19_ASR_AIShell_zh_ASR_v2_5044.wav ADDED
Binary file (133 kB). View file
 
audio_samples/1_ASR_IMDA_PART1_ASR_v2_141.wav ADDED
Binary file (152 kB). View file
 
audio_samples/20_ASR_LIBRISPEECH_CLEAN_ASR_V2_833.wav ADDED
Binary file (137 kB). View file
 
audio_samples/25_ST_COVOST2_ZH-CN_EN_ST_V2_4567.wav ADDED
Binary file (260 kB). View file
 
audio_samples/26_ST_COVOST2_EN_ZH-CN_ST_V2_5422.wav ADDED
Binary file (187 kB). View file
 
audio_samples/27_ST_COVOST2_EN_ZH-CN_ST_V2_6697.wav ADDED
Binary file (99.1 kB). View file
 
audio_samples/28_SI_ALPACA-GPT4-AUDIO_SI_V2_299.wav ADDED
Binary file (186 kB). View file
 
audio_samples/29_SI_ALPACA-GPT4-AUDIO_SI_V2_750.wav ADDED
Binary file (154 kB). View file
 
audio_samples/2_ASR_IMDA_PART1_ASR_v2_2258.wav ADDED
Binary file (97.5 kB). View file
 
audio_samples/30_SI_ALPACA-GPT4-AUDIO_SI_V2_1454.wav ADDED
Binary file (171 kB). View file
 
audio_samples/31_SI_OPENHERMES-AUDIO_SI_V2_673.wav ADDED
Binary file (423 kB). View file
 
audio_samples/32_SQA_CN_COLLEDGE_ENTRANCE_ENGLISH_TEST_SQA_V2_572.wav ADDED
Binary file (625 kB). View file
 
audio_samples/33_SQA_IMDA_PART3_30_SQA_V2_2310.wav ADDED
Binary file (928 kB). View file
 
audio_samples/34_SQA_IMDA_PART3_30_SQA_V2_3621.wav ADDED
Binary file (898 kB). View file
 
audio_samples/35_SQA_IMDA_PART3_30_SQA_V2_4062.wav ADDED
Binary file (928 kB). View file
 
audio_samples/36_DS_IMDA_PART4_30_DS_V2_849.wav ADDED
Binary file (872 kB). View file
 
audio_samples/39_Paralingual_IEMOCAP_ER_V2_91.wav ADDED
Binary file (265 kB). View file
 
audio_samples/3_ASR_IMDA_PART1_ASR_v2_2265.wav ADDED
Binary file (125 kB). View file
 
audio_samples/40_Paralingual_IEMOCAP_ER_V2_567.wav ADDED
Binary file (140 kB). View file
 
audio_samples/42_Paralingual_IEMOCAP_GR_V2_320.wav ADDED
Binary file (320 kB). View file
 
audio_samples/43_Paralingual_IEMOCAP_GR_V2_129.wav ADDED
Binary file (203 kB). View file
 
audio_samples/45_Paralingual_IMDA_PART3_30_GR_V2_12312.wav ADDED
Binary file (832 kB). View file
 
audio_samples/47_Paralingual_IMDA_PART3_30_NR_V2_10479.wav ADDED
Binary file (861 kB). View file
 
audio_samples/49_Paralingual_MELD_ER_V2_676.wav ADDED
Binary file (210 kB). View file
 
audio_samples/4_ASR_IMDA_PART2_ASR_v2_999.wav ADDED
Binary file (133 kB). View file
 
audio_samples/50_Paralingual_MELD_ER_V2_692.wav ADDED
Binary file (65.6 kB). View file
 
audio_samples/51_Paralingual_VOXCELEB1_GR_V2_2148.wav ADDED
Binary file (150 kB). View file
 
audio_samples/53_Paralingual_VOXCELEB1_NR_V2_2286.wav ADDED
Binary file (831 kB). View file
 
audio_samples/55_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_2.wav ADDED
Binary file (928 kB). View file
 
audio_samples/56_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_415.wav ADDED
Binary file (806 kB). View file
 
audio_samples/57_SQA_PUBLIC_SPEECH_SG_TEST_SQA_V2_460.wav ADDED
Binary file (928 kB). View file
 
audio_samples/5_ASR_IMDA_PART2_ASR_v2_2241.wav ADDED
Binary file (99.9 kB). View file
 
audio_samples/6_ASR_IMDA_PART2_ASR_v2_3409.wav ADDED
Binary file (140 kB). View file
 
audio_samples/7_ASR_IMDA_PART3_30_ASR_v2_2269.wav ADDED
Binary file (869 kB). View file
 
audio_samples/8_ASR_IMDA_PART3_30_ASR_v2_1698.wav ADDED
Binary file (907 kB). View file
 
audio_samples/9_ASR_IMDA_PART3_30_ASR_v2_2474.wav ADDED
Binary file (818 kB). View file
 
pages/agent.py ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ from src.content.agent import agent_page
2
+
3
+ agent_page()