ZipNN

README.md

@@ -81,7 +81,7 @@ from zipnn import zipnn_hf
 zipnn_hf()
 
 
-pipe = pipeline("automatic-speech-recognition", model="royleibov/wav2vec2-large-xlsr-53-english")
+pipe = pipeline("automatic-speech-recognition", model="royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed")
 ```
 ```python
 # Load model directly
@@ -90,22 +90,22 @@ from zipnn import zipnn_hf
 
 zipnn_hf()
 
-processor = AutoProcessor.from_pretrained("royleibov/wav2vec2-large-xlsr-53-english")
-model = AutoModelForCTC.from_pretrained("royleibov/wav2vec2-large-xlsr-53-english")
+processor = AutoProcessor.from_pretrained("royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed")
+model = AutoModelForCTC.from_pretrained("royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed")
 ```
 ### ZipNN
 ZipNN also allows you to seemlessly save local disk space in your cache after the model is downloaded.
 
 To compress the cached model, simply run:
 ```bash
-python zipnn_compress_path.py safetensors --model royleibov/granite-3.0-8b-instruct-ZipNN-Compressed --hf_cache
+python zipnn_compress_path.py safetensors --model royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed --hf_cache
 ```
 
 The model will be decompressed automatically and safely as long as `zipnn_hf()` is added at the top of the file like in the [example above](#use-this-model).
 
 To decompress manualy, simply run:
 ```bash
-python zipnn_decompress_path.py --model royleibov/granite-3.0-8b-instruct-ZipNN-Compressed --hf_cache
+python zipnn_decompress_path.py --model royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed --hf_cache
 ```
 
 # Fine-tuned XLSR-53 large model for speech recognition in English
@@ -125,8 +125,11 @@ Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library
 
 ```python
 from huggingsound import SpeechRecognitionModel
+from zipnn import zipnn_hf
+
+zipnn_hf()
 
-model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-english")
+model = SpeechRecognitionModel("royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed")
 audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
 
 transcriptions = model.transcribe(audio_paths)
@@ -139,9 +142,12 @@ import torch
 import librosa
 from datasets import load_dataset
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+from zipnn import zipnn_hf
+
+zipnn_hf()
 
 LANG_ID = "en"
-MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-english"
+MODEL_ID = "royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed"
 SAMPLES = 10
 
 test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
@@ -190,13 +196,13 @@ for i, predicted_sentence in enumerate(predicted_sentences):
 1. To evaluate on `mozilla-foundation/common_voice_6_0` with split `test`
 
 ```bash
-python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-english --dataset mozilla-foundation/common_voice_6_0 --config en --split test
+python eval.py --model_id royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed --dataset mozilla-foundation/common_voice_6_0 --config en --split test
 ```
 
 2. To evaluate on `speech-recognition-community-v2/dev_data`
 
 ```bash
-python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-english --dataset speech-recognition-community-v2/dev_data --config en --split validation --chunk_length_s 5.0 --stride_length_s 1.0
+python eval.py --model_id royleibov/wav2vec2-large-xlsr-53-english-ZipNN-Compressed --dataset speech-recognition-community-v2/dev_data --config en --split validation --chunk_length_s 5.0 --stride_length_s 1.0
 ```
 
 ## Citation