Addressing comments.

README.md

@@ -4,8 +4,8 @@ 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.
 
 This unified model enables multiple tasks without relying on multiple separate models:
 - Speech-to-speech translation (S2ST)

scripts/m4t/finetune/dataset.py

@@ -16,7 +16,9 @@ from pathlib import Path
 from stopes.hub import load_config
 from stopes.speech.tokenizers import SpeechTokenizer, SpeechTokenizerConfig
 
-from seamless_communication.datasets.hugginface import Speech2SpeechFleursDatasetBuilder
+from seamless_communication.datasets.huggingface import (
+    Speech2SpeechFleursDatasetBuilder,
+)
 
 logging.basicConfig(
     level=logging.INFO,

scripts/m4t/finetune/trainer.py

@@ -56,7 +56,7 @@ class FinetuneParams:
     """ Get eval loss after each `eval_steps` training steps """
 
     patience: int = 3
-    """ Terminate if eval loss didn not improve
+    """ Terminate if eval loss did not improve
     over the last `patience * eval_steps` training steps"""
 
     learning_rate: float = 1e-5