Update Model URLs + Notification about PyTorch versions (#2)

- Update Model URLs + Notification about PyTorch versions (814ee4dacc231a8f9e05666876014841ce123ffd)

README.md

@@ -3,6 +3,7 @@ inference: false
 tags:
 - SeamlessM4T
 license: cc-by-nc-4.0
+library_name: fairseq2
 ---
 
 # SeamlessM4T - On-Device
@@ -10,20 +11,21 @@ SeamlessM4T is designed to provide high quality translation, allowing people fro
 
 SeamlessM4T covers:
 - 📥 101 languages for speech input
-- ⌨️   96 Languages for text input/output
-- 🗣️  35 languages for speech output. 
+- ⌨️ 96 Languages for text input/output
+- 🗣️ 35 languages for speech output. 
 
 Apart from [SeamlessM4T-LARGE (2.3B)](https://huggingface.co/facebook/seamless-m4t-large) and [SeamlessM4T-MEDIUM (1.2B)](https://huggingface.co/facebook/seamless-m4t-medium) models, we are also developing a small model (281M) targeting for on-device inference.
 [This folder](https://huggingface.co/facebook/seamless-m4t-unity-small) contains an example to run an exported small model covering most tasks (ASR/S2TT/S2ST). The model could be executed on popular mobile devices with Pytorch Mobile (https://pytorch.org/mobile/home/).
 
 ## Overview
+| Model   | Checkpoint | Num Params | Disk Size | Supported Tasks         | Supported Languages|
+|---------|------------|----------|-------------|------------|-------------------------|
+| UnitY-Small|[🤗 Model card](https://huggingface.co/facebook/seamless-m4t-unity-small) - [checkpoint](https://huggingface.co/facebook/seamless-m4t-unity-small/resolve/main/unity_on_device.ptl) | 281M | 862MB        | S2ST, S2TT, ASR |eng, fra, hin, por, spa|
+| UnitY-Small-S2T |[🤗 Model card](https://huggingface.co/facebook/seamless-m4t-unity-small-s2t) - [checkpoint](https://huggingface.co/facebook/seamless-m4t-unity-small-s2t/resolve/main/unity_on_device_s2t.ptl) | 235M | 637MB        | S2TT, ASR    |eng, fra,hin,  por, spa|
 
-| Model   | Disk Size | Supported Tasks         | Supported Languages|
-|---------|----------------------|-------------------------|-------------------------|
-| [UnitY-Small](https://huggingface.co/facebook/seamless-m4t-unity-small/resolve/main/unity_on_device.ptl) | 862MB        | S2ST, S2TT, ASR |eng, fra, hin, por, spa|
-| [UnitY-Small-S2T](https://huggingface.co/facebook/seamless-m4t-unity-small-s2t/resolve/main/unity_on_device_s2t.ptl) | 637MB        | S2TT, ASR    |eng, fra, hin, por, spa|
+UnitY-Small-S2T is a pruned version of UnitY-Small without 2nd pass unit decoding.
 
-[UnitY-Small-S2T](https://huggingface.co/facebook/seamless-m4t-unity-small-s2t) is a pruned version of [UnitY-Small](https://huggingface.co/facebook/seamless-m4t-unity-small) without 2nd pass unit decoding. Unlike [UnitY-Small](https://huggingface.co/facebook/seamless-m4t-unity-small), it can only be used for ASR and S2TT tasks.
+Note: If using pytorch runtime in python, only **pytorch<=1.11.0** is supported for **UnitY-Small(281M)**. We tested UnitY-Small-S2T(235M), it works with later versions. 
 
 ## Inference
 To use exported model, users don't need seamless_communication or fairseq2 dependency.