Update README.md

README.md

@@ -36,6 +36,12 @@ model-index:
 
 Fine-tuned [facebook/wav2vec2-base-fr-voxpopuli-v2](https://huggingface.co/facebook/wav2vec2-base-fr-voxpopuli-v2) for **French speech-to-phoneme** using the train and validation splits of [Common Voice v13](https://huggingface.co/datasets/mozilla-foundation/common_voice_13_0).
 
+## Samplerate of audio 
+
+When using this model, make sure that your speech input is **sampled at 16kHz**.
+
+## Training procedure details
+
 - The model has been trained for 14 epochs on 4x2080 Ti GPUs using a ddp strategy and gradient-accumulation procedure (256 audios per update, corresponding roughly to 25 minutes of speech per update -> 2k updates per epoch)
 - Learning rate schedule : Double Tri-state schedule
     - Warmup from 1e-5 for 7% of total updates
@@ -47,5 +53,3 @@ Fine-tuned [facebook/wav2vec2-base-fr-voxpopuli-v2](https://huggingface.co/faceb
  
 - The set of hyperparameters used for training are those detailed in Annex B and Table 6 of [wav2vec2 paper](https://arxiv.org/pdf/2006.11477.pdf).
 
-When using this model, make sure that your speech input is **sampled at 16kHz**.
-