Update README.md

README.md

@@ -33,7 +33,7 @@ The ASR system is composed of:
 - the **Acoustic model** (wav2vec2.0 + DNN + CTC greedy decode). The pretrained wav2vec 2.0 model [LeBenchmark/wav2vec2-FR-7K-large](https://huggingface.co/LeBenchmark/wav2vec2-FR-7K-large) is combined with two DNN layers and fine-tuned on Orféo.
 The final acoustic representation is given to the CTC greedy decode.
 
-We used recordings sampled at 16kHz (single channel).
+We used recordings sampled at 16kHz (single channel). For training, we did not use audio files longer than 10 seconds to prevent memory issues.
 
 ## 💻 How to transcribe a file with the model