Update README.md
Browse files
README.md
CHANGED
|
@@ -26,8 +26,6 @@ tags:
|
|
| 26 |
|
| 27 |
A multilingual machine-translation model covering English and 12 Indian languages, trained from scratch in the M2M100 architecture. It translates directly between any supported pair (not only to and from English).
|
| 28 |
|
| 29 |
-
> Early research checkpoint. This is an initial from-scratch model; quality varies by language pair. Treat it as a baseline to build on, not a production-grade system.
|
| 30 |
-
|
| 31 |
**Version:** `v2` 路 **Languages:** English, Hindi, Bengali, Marathi, Tamil, Telugu, Kannada, Malayalam, Odia, Gujarati, Punjabi, Assamese, Urdu.
|
| 32 |
|
| 33 |
## What this model is for
|
|
@@ -74,7 +72,6 @@ print(translate("How are you?", "en", "hi"))
|
|
| 74 |
|
| 75 |
## Limitations
|
| 76 |
|
| 77 |
-
- Early checkpoint -- fluency and adequacy trail mature MT systems, especially on long or domain-specific sentences.
|
| 78 |
- Best on short-to-medium sentences; very long inputs are truncated at encode time.
|
| 79 |
- No guarantee of terminology consistency or safe handling of code-mixed input.
|
| 80 |
|
|
|
|
| 26 |
|
| 27 |
A multilingual machine-translation model covering English and 12 Indian languages, trained from scratch in the M2M100 architecture. It translates directly between any supported pair (not only to and from English).
|
| 28 |
|
|
|
|
|
|
|
| 29 |
**Version:** `v2` 路 **Languages:** English, Hindi, Bengali, Marathi, Tamil, Telugu, Kannada, Malayalam, Odia, Gujarati, Punjabi, Assamese, Urdu.
|
| 30 |
|
| 31 |
## What this model is for
|
|
|
|
| 72 |
|
| 73 |
## Limitations
|
| 74 |
|
|
|
|
| 75 |
- Best on short-to-medium sentences; very long inputs are truncated at encode time.
|
| 76 |
- No guarantee of terminology consistency or safe handling of code-mixed input.
|
| 77 |
|