Few edits & typos

.github/workflows/build_and_publish_to_pypi.yml

@@ -1,10 +1,10 @@
-name: Publish Python 🐍 distributions 📦 to PyPI
+name: Publish Python distributions to PyPI
 
 on: push
 
 jobs:
   build-n-publish:
-    name: Build and publish Python 🐍 distributions 📦 to PyPI
+    name: Build and publish Python distributions to PyPI
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@master
@@ -22,7 +22,7 @@ jobs:
       run: >-
         python -m
         build
-    - name: Publish distribution 📦 to PyPI
+    - name: Publish distribution to PyPI
       if: startsWith(github.ref, 'refs/tags')
       uses: pypa/gh-action-pypi-publish@release/v1
       with:

README.md

@@ -68,7 +68,7 @@ openWakeword models are composed of three separate components:
 
 1) A pre-processing function that computes [melspectrogram](https://pytorch.org/audio/main/generated/torchaudio.transforms.MelSpectrogram.html) of the input audio data. For openWakeword, an ONNX implementation of Torch's melspectrogram function with fixed parameters is used to enable efficient performance across devices.
 
-2) A shared feature extraction backbone model that converts melspectrogram inputs into general-purpose speech audio embeddings. This [model](https://arxiv.org/abs/2002.01322) is provided by [Google](https://tfhub.dev/google/speech_embedding/1) as a TFHub module under an [Apache-2.0](https://opensource.org/licenses/Apache-2.0) license. For openWakeWord, this model was manually re-implemented to separate out different functionality and allow for more control of architecture modifications compared to a TFHub module. The model itself is series of relatively simple convoluational blocks, and gains its strong performance from extensive pre-training on large amounts of data. This model is the core component of openWakeWord, and enables the [strong performance](#-Performance-and-Evaluation) that is seen even when training on fully-synthetic data.
+2) A shared feature extraction backbone model that converts melspectrogram inputs into general-purpose speech audio embeddings. This [model](https://arxiv.org/abs/2002.01322) is provided by [Google](https://tfhub.dev/google/speech_embedding/1) as a TFHub module under an [Apache-2.0](https://opensource.org/licenses/Apache-2.0) license. For openWakeWord, this model was manually re-implemented to separate out different functionality and allow for more control of architecture modifications compared to a TFHub module. The model itself is series of relatively simple convoluational blocks, and gains its strong performance from extensive pre-training on large amounts of data. This model is the core component of openWakeWord, and enables the strong performance that is seen even when training on fully-synthetic data.
 
 3) A classification model that follows the shared (and frozen) feature extraction model. The structure of this classification model is arbitrary, but in practice a simple fully-connected network or 2 layer RNN works well.
 
@@ -102,11 +102,11 @@ As a second illustration, the false-accept/false-reject rate of the included `"h
 
 ![FPR/FRR curve for "hey mycroft" pre-trained model](docs/models/images/hey_mycroft_performance.png)
 
-Again, for at least this test data and prepration, openWakeWord produces a model more accurate than existing solutions.
+Again, for at least this test data and prepration, openWakeWord produces a model at least as good as existing solutions.
 
-*However*, in should noted that for both of these tests sample sizes are small and there are issues ([1](https://github.com/Picovoice/wake-word-benchmark/issues/13), [2](https://github.com/MycroftAI/mycroft-precise/issues/237)) with the evaluation of the other libraries that suggest these results should be interpreted cautiously. As such, the only claim being made is that openWakeWord models are broadly competitive with comparable offerings. You are strongly encouraged to [test openWakeWord yourself](#installation--usage) to determine if it will meet the requirements of your use-case.
+However, in should noted that for both of these tests sample sizes are small and there are issues ([1](https://github.com/Picovoice/wake-word-benchmark/issues/13), [2](https://github.com/MycroftAI/mycroft-precise/issues/237)) with the evaluation of the other libraries that suggest these results should be interpreted cautiously. As such, the only claim being made is that openWakeWord models are broadly competitive with comparable offerings. You are strongly encouraged to [test openWakeWord](#installation--usage) to determine if it will meet the requirements of your use-case.
 
-Finally, to give evidence that the core methods behind openWakeWord (i.e., pre-trained speech embeddings and high-quality synthetic speech) are effective across a wider range of wake word/phrase structure and length, the table below shows the performance on the [Fluent Speech Commands](https://paperswithcode.com/sota/spoken-language-understanding-on-fluent) test set using an openWakeWord model and the baseline method shown in a [related paper by the dataset authors](https://arxiv.org/abs/1910.09463). Note that due to fundamentally different data preparation, training, and evaluation approaches between the two models the overall conclusion should only be that openWakeWord is likely equally capable compared to a more complex (and significantly larger) model in the task of spoken language understanding (SLU).
+Finally, to give evidence that the core methods behind openWakeWord (i.e., pre-trained speech embeddings and high-quality synthetic speech) are effective across a wider range of wake word/phrase structure and length, the table below shows the performance on the [Fluent Speech Commands](https://paperswithcode.com/sota/spoken-language-understanding-on-fluent) test set using an openWakeWord model and the baseline method shown in a [related paper by the dataset authors](https://arxiv.org/abs/1910.09463). While both models were trained on fully-synthetic data, due to fundamentally different data synthesis & preparation, training, and evaluation approaches, the numbers below are likely not directly comparable. Rather, the important conclusion is that openWakeWord is a viable approach for the task of spoken language understanding (SLU).
 
 | Model | Test Set Accuracy | Link |
 | ------------- | ------------- | ------------- |