Update README.md
Browse files
README.md
CHANGED
@@ -122,8 +122,10 @@ language:
|
|
122 |
- yo
|
123 |
- zh
|
124 |
---
|
|
|
125 |
|
126 |
|
|
|
127 |
|
128 |
# Table of Contents:
|
129 |
|
@@ -131,7 +133,7 @@ language:
|
|
131 |
2. [Training Data and Code](https://huggingface.co/utter-project/mHuBERT-147#training)
|
132 |
3. [ML-SUPERB Scores](https://huggingface.co/utter-project/mHuBERT-147#ml-superb-scores)
|
133 |
4. [Languages and Datasets](https://huggingface.co/utter-project/mHuBERT-147#languages-and-datasets)
|
134 |
-
|
135 |
|
136 |
# mHuBERT-147 models
|
137 |
|
@@ -141,10 +143,13 @@ Training employs a two-level language, data source up-sampling during training.
|
|
141 |
|
142 |
**This repository contains:**
|
143 |
* Fairseq checkpoint (original);
|
144 |
-
* HuggingFace checkpoint;
|
145 |
* Faiss index for continuous pre-training (OPQ16_64,IVF1000_HNSW32,PQ16x4fsr).
|
146 |
|
147 |
-
**
|
|
|
|
|
|
|
148 |
|
149 |
# Training
|
150 |
|
|
|
122 |
- yo
|
123 |
- zh
|
124 |
---
|
125 |
+
**This repository contains the best mHuBERT-147 model.**
|
126 |
|
127 |
|
128 |
+
**MODEL DETAILS:** 3rd iteration, K=1000, HuBERT base architecture (95M parameters), 147 languages.
|
129 |
|
130 |
# Table of Contents:
|
131 |
|
|
|
133 |
2. [Training Data and Code](https://huggingface.co/utter-project/mHuBERT-147#training)
|
134 |
3. [ML-SUPERB Scores](https://huggingface.co/utter-project/mHuBERT-147#ml-superb-scores)
|
135 |
4. [Languages and Datasets](https://huggingface.co/utter-project/mHuBERT-147#languages-and-datasets)
|
136 |
+
6. [Citing and Funding Information](https://huggingface.co/utter-project/mHuBERT-147#citing-and-funding-information)
|
137 |
|
138 |
# mHuBERT-147 models
|
139 |
|
|
|
143 |
|
144 |
**This repository contains:**
|
145 |
* Fairseq checkpoint (original);
|
146 |
+
* HuggingFace checkpoint (conversion using transformers library);
|
147 |
* Faiss index for continuous pre-training (OPQ16_64,IVF1000_HNSW32,PQ16x4fsr).
|
148 |
|
149 |
+
**Related Models:**
|
150 |
+
* Second Iteration repository: https://huggingface.co/utter-project/mHuBERT-147-base-2nd-iter
|
151 |
+
* First Iteration repository: https://huggingface.co/utter-project/mHuBERT-147-base-1st-iter
|
152 |
+
* CommonVoice Prototype (12 languages): https://huggingface.co/utter-project/hutter-12-3rd-base
|
153 |
|
154 |
# Training
|
155 |
|