Update weights (#3)

- Update weights and README.md (ca3a1fdbf88967caf76ba804613d4df0999d0a5e)


Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.ptl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -14,9 +14,9 @@ SeamlessM4T covers:
 - ⌨️ 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-s2t)) contains an example to run an exported small model covering ASR and S2TT. The model could be executed on popular mobile devices with Pytorch Mobile (https://pytorch.org/mobile/home/). 
+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.
 
-Refer to [UnitY-Small](https://huggingface.co/facebook/seamless-m4t-unity-small) if you also wish to cover speech-to-speech translation (S2ST) in addition to ASR and S2TT tasks. 
+This README 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|
@@ -26,30 +26,27 @@ Refer to [UnitY-Small](https://huggingface.co/facebook/seamless-m4t-unity-small)
 
 UnitY-Small-S2T is a pruned version of UnitY-Small without 2nd pass unit decoding.
 
-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.
 
 ```python
 import torchaudio
 import torch
+
 audio_input, _ = torchaudio.load(TEST_AUDIO_PATH) # Load waveform using torchaudio
 
 s2t_model = torch.jit.load("unity_on_device_s2t.ptl") # Load exported S2T model
-text = s2t_model(audio_input, tgt_lang=TGT_LANG) # Forward call with tgt_lang specified for ASR or S2TT
-print(f"{lang}:{text}")
 
-s2st_model = torch.jit.load("unity_on_device.ptl")
-text, units, waveform = s2st_model(audio_input, tgt_lang=TGT_LANG) # S2ST model also returns waveform
-print(f"{lang}:{text}")
-torchaudio.save(f"{OUTPUT_FOLDER}/{lang}.wav", waveform.unsqueeze(0), sample_rate=16000) # Save output waveform to local file
+with torch.no_grad():
+    text = s2t_model(audio_input, tgt_lang=TGT_LANG) # Forward call with tgt_lang specified for ASR or S2TT
+
+print(text) # Show text output 
 ```
 
 Also running the exported model doesn't need python runtime. For example, you could load this model in C++ following [this tutorial](https://pytorch.org/tutorials/advanced/cpp_export.html), or building your own on-device applications similar to [this example](https://github.com/pytorch/ios-demo-app/tree/master/SpeechRecognition)
 
 # Citation
-If you use SeamlessM4T in your work or any models/datasets/artifacts published in SeamlessM4T, please cite :
+If you use SeamlessM4T in your work or any models/datasets/artifacts published in SeamlessM4T, please cite:
 
 ```bibtex
 @article{seamlessm4t2023,
@@ -61,4 +58,4 @@ If you use SeamlessM4T in your work or any models/datasets/artifacts published i
 ```
 # License
 
-seamless_communication is CC-BY-NC 4.0 licensed
+seamless_communication is CC-BY-NC 4.0 licensed

unity_on_device_s2t.ptl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230b8cd72c6eac9b7d021e2edf7b865a89dcc410b49bf6835c817fc16dcd5f01
-size 667605684
+oid sha256:834591dbf6df69dd08f93ab303b7d506df8830552b8472818cc16c7564b2b9df
+size 504153032