mattChrisP commited on
Commit
4801476
·
1 Parent(s): eced458

Add release-v2 demo comparisons

Browse files

Add the corrected release.csv-ordered comparison set; use Stage-2 Thinker + Stage-4 Talker for Myna-Hokkien; remove legacy sample 05 and the legacy day-off-email sample.

This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +19 -2
  2. demo_samples/{05/05_input.wav → release_csv/01/01_gemini.wav} +2 -2
  3. demo_samples/release_csv/01/01_glmvoice.wav +3 -0
  4. demo_samples/release_csv/01/01_gptaudio.wav +3 -0
  5. demo_samples/{05/05_gptaudio.wav → release_csv/01/01_input.wav} +2 -2
  6. demo_samples/{05/05_mynahokkien.wav → release_csv/01/01_mynahokkien.wav} +1 -1
  7. demo_samples/release_csv/01/01_qwen.wav +3 -0
  8. demo_samples/release_csv/02/02_gemini.wav +3 -0
  9. demo_samples/release_csv/02/02_glmvoice.wav +3 -0
  10. demo_samples/release_csv/02/02_gptaudio.wav +3 -0
  11. demo_samples/release_csv/02/02_input.wav +3 -0
  12. demo_samples/release_csv/02/02_mynahokkien.wav +3 -0
  13. demo_samples/release_csv/02/02_qwen.wav +3 -0
  14. demo_samples/release_csv/03/03_gemini.wav +3 -0
  15. demo_samples/release_csv/03/03_glmvoice.wav +3 -0
  16. demo_samples/release_csv/03/03_gptaudio.wav +3 -0
  17. demo_samples/release_csv/03/03_input.wav +3 -0
  18. demo_samples/release_csv/03/03_mynahokkien.wav +3 -0
  19. demo_samples/release_csv/03/03_qwen.wav +3 -0
  20. demo_samples/release_csv/04/04_gemini.wav +3 -0
  21. demo_samples/release_csv/04/04_glmvoice.wav +3 -0
  22. demo_samples/release_csv/04/04_gptaudio.wav +3 -0
  23. demo_samples/release_csv/04/04_input.wav +3 -0
  24. demo_samples/release_csv/04/04_mynahokkien.wav +3 -0
  25. demo_samples/release_csv/04/04_qwen.wav +3 -0
  26. demo_samples/{05 → release_csv/05}/05_gemini.wav +2 -2
  27. demo_samples/{05 → release_csv/05}/05_glmvoice.wav +2 -2
  28. demo_samples/release_csv/05/05_gptaudio.wav +3 -0
  29. demo_samples/release_csv/05/05_input.wav +3 -0
  30. demo_samples/release_csv/05/05_mynahokkien.wav +3 -0
  31. demo_samples/{05 → release_csv/05}/05_qwen.wav +2 -2
  32. demo_samples/release_csv/06/06_gemini.wav +3 -0
  33. demo_samples/release_csv/06/06_glmvoice.wav +3 -0
  34. demo_samples/release_csv/06/06_gptaudio.wav +3 -0
  35. demo_samples/release_csv/06/06_input.wav +3 -0
  36. demo_samples/release_csv/06/06_mynahokkien.wav +3 -0
  37. demo_samples/release_csv/06/06_qwen.wav +3 -0
  38. demo_samples/release_csv/07/07_gemini.wav +3 -0
  39. demo_samples/release_csv/07/07_glmvoice.wav +3 -0
  40. demo_samples/release_csv/07/07_gptaudio.wav +3 -0
  41. demo_samples/release_csv/07/07_input.wav +3 -0
  42. demo_samples/release_csv/07/07_mynahokkien.wav +3 -0
  43. demo_samples/release_csv/07/07_qwen.wav +3 -0
  44. demo_samples/release_csv/08/08_gemini.wav +3 -0
  45. demo_samples/release_csv/08/08_glmvoice.wav +3 -0
  46. demo_samples/release_csv/08/08_gptaudio.wav +3 -0
  47. demo_samples/release_csv/08/08_input.wav +3 -0
  48. demo_samples/release_csv/08/08_mynahokkien.wav +3 -0
  49. demo_samples/release_csv/08/08_qwen.wav +3 -0
  50. demo_samples/release_csv/09/09_gemini.wav +3 -0
README.md CHANGED
@@ -37,19 +37,36 @@ For comparison, we also ran the same inputs through four frontier audio-to-audio
37
  none of which officially supports Hokkien;
38
  we include them to illustrate how far mainstream omni models are from handling the language, not as an apples-to-apples benchmark.
39
 
 
 
40
  | Input | Myna-Hokkien | GPT Audio | Qwen3.5-Omni-Plus | Gemini | GLM-Voice |
41
  |-------|-------------|-----------|--------------------|--------|-----------|
42
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_glmvoice.wav"></audio> |
43
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_glmvoice.wav"></audio> |
44
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_glmvoice.wav"></audio> |
45
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_glmvoice.wav"></audio> |
46
- | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/05/05_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/05/05_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/05/05_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/05/05_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/05/05_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/05/05_glmvoice.wav"></audio> |
47
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_glmvoice.wav"></audio> |
48
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_glmvoice.wav"></audio> |
49
- | Draft an email for me to request to take a day off at work. | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/08_en_text/08_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/08_en_text/08_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/08_en_text/08_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/08_en_text/08_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/08_en_text/08_glmvoice.wav"></audio> |
50
  | I'm feeling awful today. | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_glmvoice.wav"></audio> |
51
  | 我今天心情有点不好。 | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_glmvoice.wav"></audio> |
52
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
  ## Installation
55
 
 
37
  none of which officially supports Hokkien;
38
  we include them to illustrate how far mainstream omni models are from handling the language, not as an apples-to-apples benchmark.
39
 
40
+ ### Earlier demo samples
41
+
42
  | Input | Myna-Hokkien | GPT Audio | Qwen3.5-Omni-Plus | Gemini | GLM-Voice |
43
  |-------|-------------|-----------|--------------------|--------|-----------|
44
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/01/01_glmvoice.wav"></audio> |
45
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/02/02_glmvoice.wav"></audio> |
46
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/03/03_glmvoice.wav"></audio> |
47
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/04/04_glmvoice.wav"></audio> |
 
48
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/06/06_glmvoice.wav"></audio> |
49
  | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_input.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/07/07_glmvoice.wav"></audio> |
 
50
  | I'm feeling awful today. | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/09_en_text/09_glmvoice.wav"></audio> |
51
  | 我今天心情有点不好。 | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/10_zh_text/10_glmvoice.wav"></audio> |
52
 
53
+ ### Release-v2 evaluation samples
54
+
55
+ These samples follow the ordering in the release CSV. The Myna-Hokkien column is generated by the current-best release-v2 stack: **Stage-2 Thinker + Stage-4 Talker**.
56
+
57
+ | Input | Myna-Hokkien | GPT Audio | Qwen3.5-Omni-Plus | Gemini | GLM-Voice |
58
+ |-------|-------------|-----------|--------------------|--------|-----------|
59
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/01/01_input.wav"></audio><br><sub>Very sian, life no meaning</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/01/01_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/01/01_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/01/01_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/01/01_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/01/01_glmvoice.wav"></audio> |
60
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/02/02_input.wav"></audio><br><sub>Today my mood very down</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/02/02_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/02/02_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/02/02_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/02/02_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/02/02_glmvoice.wav"></audio> |
61
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/03/03_input.wav"></audio><br><sub>Very angry; recommend a song</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/03/03_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/03/03_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/03/03_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/03/03_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/03/03_glmvoice.wav"></audio> |
62
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/04/04_input.wav"></audio><br><sub>Birthday pronunciation</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/04/04_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/04/04_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/04/04_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/04/04_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/04/04_glmvoice.wav"></audio> |
63
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/05/05_input.wav"></audio><br><sub>Write an email to ask for leave</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/05/05_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/05/05_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/05/05_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/05/05_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/05/05_glmvoice.wav"></audio> |
64
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/06/06_input.wav"></audio><br><sub>Want to start a business—what do you recommend?</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/06/06_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/06/06_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/06/06_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/06/06_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/06/06_glmvoice.wav"></audio> |
65
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/07/07_input.wav"></audio><br><sub>Can you tell me a joke?</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/07/07_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/07/07_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/07/07_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/07/07_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/07/07_glmvoice.wav"></audio> |
66
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/08/08_input.wav"></audio><br><sub>Recently very bothered—how can I feel less bothered?</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/08/08_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/08/08_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/08/08_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/08/08_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/08/08_glmvoice.wav"></audio> |
67
+ | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/09/09_input.wav"></audio><br><sub>Where is cheaper nearby for a haircut?</sub> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/09/09_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/09/09_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/09/09_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/09/09_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/09/09_glmvoice.wav"></audio> |
68
+ | Draft an email for me to request to take a day off at work. | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/10/10_mynahokkien.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/10/10_gptaudio.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/10/10_qwen.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/10/10_gemini.wav"></audio> | <audio controls src="https://huggingface.co/iNLP-Lab/MynaHokkien/resolve/main/demo_samples/release_csv/10/10_glmvoice.wav"></audio> |
69
+
70
 
71
  ## Installation
72
 
demo_samples/{05/05_input.wav → release_csv/01/01_gemini.wav} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe21f26b571496c1cfff99abdfe107bf390be38761b3b58d586e2b9bd0018397
3
- size 737358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c8981b53a89bdac4e17111b786987763f37a0239d7819593f51a05fa8e92a9
3
+ size 283246
demo_samples/release_csv/01/01_glmvoice.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377290ba32ea397489710327b7f2814e0101b5fea6785c3af7d6be269bf1b533
3
+ size 483372
demo_samples/release_csv/01/01_gptaudio.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1acb2b38d16e2aaabe968a3cac43e30a2439c9a8fa890ed537d28d3c2dcd178
3
+ size 504044
demo_samples/{05/05_gptaudio.wav → release_csv/01/01_input.wav} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c599238c7dc534260d3b61330d8cc6b6f02675b1309c98ca8783815a91151031
3
- size 1663244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71f5d6bfbe3949e7b552dabfa25e420d626e8ac93369e997a658bdcf69842c2
3
+ size 1560678
demo_samples/{05/05_mynahokkien.wav → release_csv/01/01_mynahokkien.wav} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b78952833f04c212f58781d3a5604b0d7cfdd72797571ba1ce6e78c8b2d043f
3
  size 256214
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca3b47f879c3c8037122a1bb70679570b3eb0647921a459faf137fd65a1429f
3
  size 256214
demo_samples/release_csv/01/01_qwen.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed18438a5b5acec0d2ff058d33696f3c1bcd208f48a655c44cfa157af634d5a9
3
+ size 157484
demo_samples/release_csv/02/02_gemini.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d411cf1ec12b081c3ce0db15f33543e85c3ee45b4a9e1ae2072259aaa405c5a9
3
+ size 318766
demo_samples/release_csv/02/02_glmvoice.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec3d679caae18d348fb34c5e6e626df93267373eb1984a6e320fcbb2e1bf0e8
3
+ size 228908
demo_samples/release_csv/02/02_gptaudio.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4ccefb50afd5f8aad01a8326b993c87ead20b00d2131d78a4dfe896285024d
3
+ size 240044
demo_samples/release_csv/02/02_input.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f37ebadb6c0f46cf534e70de4d991bc182881f20e1e84141333bdf9dfed898
3
+ size 1155174
demo_samples/release_csv/02/02_mynahokkien.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6eb44efd04387d97330ec06f25a181068bc4bb15f3c7fb116ab8766c625168
3
+ size 179414
demo_samples/release_csv/02/02_qwen.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ade89560fde2984cb9d090d632b8b62369f6011e555c7f73fe33cad94beeb0b
3
+ size 99884
demo_samples/release_csv/03/03_gemini.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b44c40338e7b23d9b260c1a2ce35de39193be3b5be51c8a2812ac133a7bf45
3
+ size 491566
demo_samples/release_csv/03/03_glmvoice.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:387d24195745c11380f8ff4076a6ded470edd628c00535b82a409a2b5ed8da86
3
+ size 2042412
demo_samples/release_csv/03/03_gptaudio.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83a8f054ec2cc200771bc57537da1f3ebaa5894082e7d39bd11a5776243851f4
3
+ size 571244
demo_samples/release_csv/03/03_input.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3d945437b407326904433f2498255ca2850eb183c614feb1a4ef6cc39d16c09
3
+ size 974926
demo_samples/release_csv/03/03_mynahokkien.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1afed5a7199de1258525f74687738db86f7f6e0e5f83dab1a8c1e8e3af69ffa7
3
+ size 225494
demo_samples/release_csv/03/03_qwen.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75c1dbcae46481544c7f89b311381a4b9866190d0727f24420592b941a72497
3
+ size 230444
demo_samples/release_csv/04/04_gemini.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df77e30f15cd19b810dba80e2198bd2ea2d3951f3cef3022f694f70f51243310
3
+ size 282286
demo_samples/release_csv/04/04_glmvoice.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae95a106b26148eb0766542657620bd50a8604403a38aa41a2860e17bb46037
3
+ size 6614572
demo_samples/release_csv/04/04_gptaudio.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d795ea580009f4b6b0d9f5994339dff5d6887385da1542988f7ef4687cfbf9ae
3
+ size 957644
demo_samples/release_csv/04/04_input.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17154d9616ce7b55ba0b478ac42292c2c868e5151c970e48c8fda95ae5b3a10
3
+ size 1597542
demo_samples/release_csv/04/04_mynahokkien.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98fb1f99e2b5540a1d826856f6ac735183ced1966b7245649a683b25515c1f10
3
+ size 194774
demo_samples/release_csv/04/04_qwen.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14dcd8ed881b45da3b3f4dbb7880b36cf5595c93c1e976b3b57d000736742d20
3
+ size 172844
demo_samples/{05 → release_csv/05}/05_gemini.wav RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59f7478fe346dbdb40b253dfeaed548cf1f8843343d3708ffd7c7dfb588470f1
3
- size 915914
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd3f422e4c2dcf2fed091f88fb22d49c29e441176941f6da52e44e87d8fb9538
3
+ size 419086
demo_samples/{05 → release_csv/05}/05_glmvoice.wav RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c4c9ab6c8726e942ee1eecba9cdd29f25bb404ed16c7ea1acf2284256eed946
3
- size 588844
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496df0db2bfeb33d38e8875f86d525f9be202048e187ad1892cc20dbd798fa68
3
+ size 472620
demo_samples/release_csv/05/05_gptaudio.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e84ea3a842a893957715c90d8a426dc572981334ae5fee5864c2036188d9495f
3
+ size 345644
demo_samples/release_csv/05/05_input.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7452da3712827440c674aa37109dbbc6c16932eb664ea9fabf42a68755ad48cf
3
+ size 1941606
demo_samples/release_csv/05/05_mynahokkien.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9171ffd61d32ae0f2fe7bf0f214cc016a0358f806ede246e399e996f1f16b76
3
+ size 179414
demo_samples/{05 → release_csv/05}/05_qwen.wav RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e2e0c24a760d5d95b6fcf7b37a9d1082cdb05bddcdc295e4d28c5cd4fc3a0a8
3
- size 103724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a021427dd029ed591479c9e18718fe8a034cced82c926c47dcd02dedd63596f0
3
+ size 126764
demo_samples/release_csv/06/06_gemini.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db23c52e56a7f9e1e2b4aa720178d302cdd2ee33a1c8254d2d63aabec694236e
3
+ size 666286
demo_samples/release_csv/06/06_glmvoice.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb303cf57c8e4c5a5e9a9bcddf2599e44f9207e86ebc0b4ebeedfc6d6e2f1e8
3
+ size 1562668
demo_samples/release_csv/06/06_gptaudio.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d822eebd35ed59ad18a7270fd43bb756077eab8fbe8b990b437d8a22d3c209c9
3
+ size 1833644
demo_samples/release_csv/06/06_input.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fac6d2eb530852f62d771f9ef0c9bb8a1ad96f5a6d60f9e9b886890e8836c6f
3
+ size 1142886
demo_samples/release_csv/06/06_mynahokkien.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15c86185fa0547608cd59406c431746564324f1ed411c096da7f93ae733b0093
3
+ size 190934
demo_samples/release_csv/06/06_qwen.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3720f57a19ccd29d38628d55667b57c30c078d1759bb9b6c8100efa896d4032
3
+ size 430124
demo_samples/release_csv/07/07_gemini.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f2f0ebae3a968fe41a0ec991f26fd7ebea92dcbbe2d4b49bc61a78a36e903e
3
+ size 313006
demo_samples/release_csv/07/07_glmvoice.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e125e026597b22b339c6c0d2dfe4bc57bbe3630c3c8577f25302e487f22a33
3
+ size 1432108
demo_samples/release_csv/07/07_gptaudio.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7adbe59113e792672115d7cf0fd7225628c1275c0c476ab1310607f72d4484df
3
+ size 842444
demo_samples/release_csv/07/07_input.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9767f581782a769dfa16b261129dfbaa14d07fe5b8dfac4cf84ba215a090e556
3
+ size 897126
demo_samples/release_csv/07/07_mynahokkien.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7859a64e09ff1bc96909669b580f474693244ada191bd2f03f7fb6d888e5b93
3
+ size 171734
demo_samples/release_csv/07/07_qwen.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e60638f088e4ce7cdd768ca3cf61747359de1b4128cf66899990fbf999237c0d
3
+ size 115244
demo_samples/release_csv/08/08_gemini.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f238a6f2fa8dcdcbd017b579ea62d5d8ef2d3298a0e7db555d35b1abb37ec3b2
3
+ size 670154
demo_samples/release_csv/08/08_glmvoice.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9ff1b557a01fa3d9d3f414e053dfa20e0ae27446760b106815db50a566ae74
3
+ size 260652
demo_samples/release_csv/08/08_gptaudio.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b6d70f6350126fdb2968faf4d3e11fc70234f3635ad419ac09339f1c60fc15
3
+ size 832844
demo_samples/release_csv/08/08_input.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7dba4b9df90d80736f4f51682c66e9b655c5079b1ab731121b2e48558d4f40
3
+ size 1228902
demo_samples/release_csv/08/08_mynahokkien.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8239ad2521118268bb610680d306453fd4118d04232e3423683c23a29065cd
3
+ size 202454
demo_samples/release_csv/08/08_qwen.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:319c45c76d4f991d6e19b97dd7b56f425b4be1d5cd745ced316e88eed07a3463
3
+ size 188204
demo_samples/release_csv/09/09_gemini.wav ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a9fe4a8bf7aefd93344e881d682e90cc52ad5a95644980811e4aaffc454082
3
+ size 464206