This is a demonstration of a language guesser, as proposed in Cavnar, Trenkle, N-Gram-Based Text Categorization. It's implemented in Perl. You can get the Perl script under certain copyright restrictions here. For free! No commercial version available!
LIST OF LANGUAGES currently supported.
But some languages are only supported in certain encodings...
1. afrikaans
2. albanian
3. amharic-utf
4. arabic-iso8859_6
5. arabic-windows1256
6. armenian
7. basque
8. belarus-windows1251
9. bosnian
10. breton
11. bulgarian-iso8859_5
12. catalan
13. chinese-big5
14. chinese-gb2312
15. croatian-ascii
16. czech-iso8859_2
17. danish
18. dutch
19. english
20. esperanto
21. estonian
22. finnish
23. french
24. frisian
25. georgian
26. german
27. greek-iso8859-7
28. hawaian
29. hebrew-iso8859_8
30. hindi
31. hungarian
32. icelandic
33. indonesian
34. irish
35. italian
36. japanese-euc_jp
37. japanese-shift_jis
38. korean
39. latin
40. latvian
41. lithuanian
42. malay
43. manx
44. marathi
45. mf
46. mingo
47. nepali
48. norwegian
49. persian
50. polish
51. portuguese
52. quechua
53. romanian
54. rumantsch
55. russian-iso8859_5
56. russian-koi8_r
57. russian-windows1251
58. sanskrit
59. scots
60. scots_gaelic
61. serbian-ascii
62. slovak-ascii
63. slovak-windows1250
64. slovenian-ascii
65. slovenian-iso8859_2
66. spanish
67. swahili
68. swedish
69. tagalog
70. tamil
71. thai
72. turkish
73. ukrainian-koi8_u
74. vietnamese
75. welsh
76. yiddish-utf