version 0.4.6

README.md

@@ -39,19 +39,19 @@ In alternative, you can install the following standalone pre-packaged models wit
 
 | model name | source | pip package |
 |------------|--------|---|
-| en_use_md  | https://tfhub.dev/google/universal-sentence-encoder | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/en_use_md-0.4.5.tar.gz#en_use_md-0.4.5` |
-| en_use_lg  | https://tfhub.dev/google/universal-sentence-encoder-large | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/en_use_lg-0.4.5.tar.gz#en_use_lg-0.4.5` |
-| xx_use_md  | https://tfhub.dev/google/universal-sentence-encoder-multilingual | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/xx_use_md-0.4.5.tar.gz#xx_use_md-0.4.5` |
-| xx_use_lg  | https://tfhub.dev/google/universal-sentence-encoder-multilingual-large | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/xx_use_lg-0.4.5.tar.gz#xx_use_lg-0.4.5` |
+| en_use_md  | https://tfhub.dev/google/universal-sentence-encoder | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/en_use_md-0.4.6.tar.gz#en_use_md-0.4.6` |
+| en_use_lg  | https://tfhub.dev/google/universal-sentence-encoder-large | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/en_use_lg-0.4.6.tar.gz#en_use_lg-0.4.6` |
+| xx_use_md  | https://tfhub.dev/google/universal-sentence-encoder-multilingual | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/xx_use_md-0.4.6.tar.gz#xx_use_md-0.4.6` |
+| xx_use_lg  | https://tfhub.dev/google/universal-sentence-encoder-multilingual-large | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/xx_use_lg-0.4.6.tar.gz#xx_use_lg-0.4.6` |
 
 In addition, also [CMLM models](https://openreview.net/pdf?id=WDVD4lUCTzU) are now available:
 
 | model name | source | pip package |
 |------------|--------|---|
-| en_use_cmlm_md  | https://tfhub.dev/google/universal-sentence-encoder-cmlm/en-base | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/en_use_cmlm_md-0.4.5.tar.gz#en_use_cmlm_md-0.4.5` |
-| en_use_cmlm_lg  | https://tfhub.dev/google/universal-sentence-encoder-cmlm/en-large | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/en_use_cmlm_lg-0.4.5.tar.gz#en_use_cmlm_lg-0.4.5` |
-| xx_use_cmlm  | https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/xx_use_cmlm-0.4.5.tar.gz#xx_use_cmlm-0.4.5` |
-| xx_use_cmlm_br  | https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base-br | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/xx_use_cmlm_br-0.4.5.tar.gz#xx_use_cmlm_br-0.4.5` |
+| en_use_cmlm_md  | https://tfhub.dev/google/universal-sentence-encoder-cmlm/en-base | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/en_use_cmlm_md-0.4.6.tar.gz#en_use_cmlm_md-0.4.6` |
+| en_use_cmlm_lg  | https://tfhub.dev/google/universal-sentence-encoder-cmlm/en-large | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/en_use_cmlm_lg-0.4.6.tar.gz#en_use_cmlm_lg-0.4.6` |
+| xx_use_cmlm  | https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/xx_use_cmlm-0.4.6.tar.gz#xx_use_cmlm-0.4.6` |
+| xx_use_cmlm_br  | https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base-br | `pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/xx_use_cmlm_br-0.4.6.tar.gz#xx_use_cmlm_br-0.4.6` |
 
 ## Usage
 
@@ -164,11 +164,11 @@ Spacy does not restore user hooks (`UserWarning: [W109]`) therefore if you use `
 To build and upload
 ```bash
 # change version
-VERSION=0.4.5
+VERSION=0.4.6
 # change version references everywhere
 # update locally installed package
 pip install -r requirements.txt
-# build the standalone models (17)
+# build the standalone models (8)
 ./build_models.sh
 # build the archive at dist/spacy_universal_sentence_encoder-${VERSION}.tar.gz
 python setup.py sdist

build_models.sh

@@ -1,6 +1,6 @@
 set -e
 
-VERSION=0.4.5
+VERSION=0.4.6
 
 # for every model
 for MODEL_NAME in en_use_md en_use_lg xx_use_md xx_use_lg xx_use_cmlm xx_use_cmlm_br en_use_cmlm_md en_use_cmlm_lg

docker/Dockerfile

@@ -1,5 +1,5 @@
-FROM python:3.8
+FROM python:3.10-slim
 
-RUN pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.5/en_use_lg-0.4.5.tar.gz#en_use_lg-0.4.5
+RUN pip install https://github.com/MartinoMensio/spacy-universal-sentence-encoder/releases/download/v0.4.6/en_use_lg-0.4.6.tar.gz#en_use_lg-0.4.6
 
 CMD bash

setup.cfg

@@ -1,5 +1,5 @@
 [metadata]
-version = 0.4.5
+version = 0.4.6
 description = SpaCy models for using Universal Sentence Encoder from TensorFlow Hub
 description-file = README.md
 url = https://github.com/MartinoMensio/spacy-universal-sentence-encoder

spacy_universal_sentence_encoder/meta/en_use_cmlm_lg.json

@@ -1,21 +1,23 @@
 {
     "lang": "en",
     "name": "use_cmlm_lg",
-    "version": "0.4.5",
+    "version": "0.4.6",
     "spacy_version": ">=3.0,<4.0",
     "description": "TensorFlow Hub wrapper for Universal Sentence Encoder",
     "author": "Martino Mensio",
     "email": "[email protected]",
     "url": "https://github.com/MartinoMensio/spacy-universal-sentence-encoder",
     "license": "MIT",
     "requirements": [
-        "spacy-universal-sentence-encoder[multi]>=0.4.5"
+        "spacy-universal-sentence-encoder[multi]>=0.4.6"
+    ],
+    "sources": [
+        {
+            "name": "Universal Sentence Encoder CMLM English Large",
+            "url": "https://tfhub.dev/google/universal-sentence-encoder-cmlm/en-large",
+            "license": "Apache-2.0"
+        }
     ],
-    "sources": [{
-        "name": "Universal Sentence Encoder CMLM English Large",
-        "url": "https://tfhub.dev/google/universal-sentence-encoder-cmlm/en-large",
-        "license": "Apache-2.0"
-    }],
     "vectors": {
         "width": 768,
         "vectors": 0,
@@ -30,7 +32,5 @@
         "universal_sentence_encoder": "universal_sentence_encoder",
         "sentencizer": "sentencizer"
     },
-    "labels": {
-
-    }
+    "labels": {}
 }

spacy_universal_sentence_encoder/meta/en_use_cmlm_md.json

@@ -1,21 +1,23 @@
 {
     "lang": "en",
     "name": "use_cmlm_md",
-    "version": "0.4.5",
+    "version": "0.4.6",
     "spacy_version": ">=3.0,<4.0",
     "description": "TensorFlow Hub wrapper for Universal Sentence Encoder",
     "author": "Martino Mensio",
     "email": "[email protected]",
     "url": "https://github.com/MartinoMensio/spacy-universal-sentence-encoder",
     "license": "MIT",
     "requirements": [
-        "spacy-universal-sentence-encoder[multi]>=0.4.5"
+        "spacy-universal-sentence-encoder[multi]>=0.4.6"
+    ],
+    "sources": [
+        {
+            "name": "Universal Sentence Encoder CMLM English Base",
+            "url": "https://tfhub.dev/google/universal-sentence-encoder-cmlm/en-base",
+            "license": "Apache-2.0"
+        }
     ],
-    "sources": [{
-        "name": "Universal Sentence Encoder CMLM English Base",
-        "url": "https://tfhub.dev/google/universal-sentence-encoder-cmlm/en-base",
-        "license": "Apache-2.0"
-    }],
     "vectors": {
         "width": 768,
         "vectors": 0,
@@ -30,7 +32,5 @@
         "universal_sentence_encoder": "universal_sentence_encoder",
         "sentencizer": "sentencizer"
     },
-    "labels": {
-
-    }
+    "labels": {}
 }

spacy_universal_sentence_encoder/meta/en_use_lg.json

@@ -1,21 +1,23 @@
 {
     "lang": "en",
     "name": "use_lg",
-    "version": "0.4.5",
+    "version": "0.4.6",
     "spacy_version": ">=3.0,<4.0",
     "description": "TensorFlow Hub wrapper for Universal Sentence Encoder",
     "author": "Martino Mensio",
     "email": "[email protected]",
     "url": "https://github.com/MartinoMensio/spacy-universal-sentence-encoder",
     "license": "MIT",
     "requirements": [
-        "spacy-universal-sentence-encoder>=0.4.5"
+        "spacy-universal-sentence-encoder>=0.4.6"
+    ],
+    "sources": [
+        {
+            "name": "Universal Sentence Encoder - Large",
+            "url": "https://tfhub.dev/google/universal-sentence-encoder-large",
+            "license": "Apache-2.0"
+        }
     ],
-    "sources": [{
-        "name": "Universal Sentence Encoder - Large",
-        "url": "https://tfhub.dev/google/universal-sentence-encoder-large",
-        "license": "Apache-2.0"
-    }],
     "vectors": {
         "width": 512,
         "vectors": 0,
@@ -30,7 +32,5 @@
         "universal_sentence_encoder": "universal_sentence_encoder",
         "sentencizer": "sentencizer"
     },
-    "labels": {
-
-    }
+    "labels": {}
 }

spacy_universal_sentence_encoder/meta/en_use_md.json

@@ -1,21 +1,23 @@
 {
     "lang": "en",
     "name": "use_md",
-    "version": "0.4.5",
+    "version": "0.4.6",
     "spacy_version": ">=3.0,<4.0",
     "description": "TensorFlow Hub wrapper for Universal Sentence Encoder",
     "author": "Martino Mensio",
     "email": "[email protected]",
     "url": "https://github.com/MartinoMensio/spacy-universal-sentence-encoder",
     "license": "MIT",
     "requirements": [
-        "spacy-universal-sentence-encoder>=0.4.5"
+        "spacy-universal-sentence-encoder>=0.4.6"
+    ],
+    "sources": [
+        {
+            "name": "Universal Sentence Encoder",
+            "url": "https://tfhub.dev/google/universal-sentence-encoder",
+            "license": "Apache-2.0"
+        }
     ],
-    "sources": [{
-        "name": "Universal Sentence Encoder",
-        "url": "https://tfhub.dev/google/universal-sentence-encoder",
-        "license": "Apache-2.0"
-    }],
     "vectors": {
         "width": 512,
         "vectors": 0,
@@ -30,7 +32,5 @@
         "universal_sentence_encoder": "universal_sentence_encoder",
         "sentencizer": "sentencizer"
     },
-    "labels": {
-
-    }
+    "labels": {}
 }

spacy_universal_sentence_encoder/meta/xx_use_cmlm.json

@@ -1,21 +1,23 @@
 {
     "lang": "xx",
     "name": "use_cmlm",
-    "version": "0.4.5",
+    "version": "0.4.6",
     "spacy_version": ">=3.0,<4.0",
     "description": "TensorFlow Hub wrapper for Universal Sentence Encoder",
     "author": "Martino Mensio",
     "email": "[email protected]",
     "url": "https://github.com/MartinoMensio/spacy-universal-sentence-encoder",
     "license": "MIT",
     "requirements": [
-        "spacy-universal-sentence-encoder[multi]>=0.4.5"
+        "spacy-universal-sentence-encoder[multi]>=0.4.6"
+    ],
+    "sources": [
+        {
+            "name": "Universal Sentence Encoder CMLM",
+            "url": "https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base/",
+            "license": "Apache-2.0"
+        }
     ],
-    "sources": [{
-        "name": "Universal Sentence Encoder CMLM",
-        "url": "https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base/",
-        "license": "Apache-2.0"
-    }],
     "vectors": {
         "width": 768,
         "vectors": 0,
@@ -30,7 +32,5 @@
         "universal_sentence_encoder": "universal_sentence_encoder",
         "sentencizer": "sentencizer"
     },
-    "labels": {
-
-    }
+    "labels": {}
 }

spacy_universal_sentence_encoder/meta/xx_use_cmlm_br.json

@@ -1,21 +1,23 @@
 {
     "lang": "xx",
     "name": "use_cmlm_br",
-    "version": "0.4.5",
+    "version": "0.4.6",
     "spacy_version": ">=3.0,<4.0",
     "description": "TensorFlow Hub wrapper for Universal Sentence Encoder",
     "author": "Martino Mensio",
     "email": "[email protected]",
     "url": "https://github.com/MartinoMensio/spacy-universal-sentence-encoder",
     "license": "MIT",
     "requirements": [
-        "spacy-universal-sentence-encoder[multi]>=0.4.5"
+        "spacy-universal-sentence-encoder[multi]>=0.4.6"
+    ],
+    "sources": [
+        {
+            "name": "Universal Sentence Encoder CMLM Bitext Retrieval Model",
+            "url": "https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base-br",
+            "license": "Apache-2.0"
+        }
     ],
-    "sources": [{
-        "name": "Universal Sentence Encoder CMLM Bitext Retrieval Model",
-        "url": "https://tfhub.dev/google/universal-sentence-encoder-cmlm/multilingual-base-br",
-        "license": "Apache-2.0"
-    }],
     "vectors": {
         "width": 768,
         "vectors": 0,
@@ -30,7 +32,5 @@
         "universal_sentence_encoder": "universal_sentence_encoder",
         "sentencizer": "sentencizer"
     },
-    "labels": {
-
-    }
+    "labels": {}
 }

spacy_universal_sentence_encoder/meta/xx_use_lg.json

@@ -1,21 +1,23 @@
 {
     "lang": "xx",
     "name": "use_lg",
-    "version": "0.4.5",
+    "version": "0.4.6",
     "spacy_version": ">=3.0,<4.0",
     "description": "TensorFlow Hub wrapper for Universal Sentence Encoder",
     "author": "Martino Mensio",
     "email": "[email protected]",
     "url": "https://github.com/MartinoMensio/spacy-universal-sentence-encoder",
     "license": "MIT",
     "requirements": [
-        "spacy-universal-sentence-encoder[multi]>=0.4.5"
+        "spacy-universal-sentence-encoder[multi]>=0.4.6"
+    ],
+    "sources": [
+        {
+            "name": "Universal Sentence Encoder Multilingual - Large",
+            "url": "https://tfhub.dev/google/universal-sentence-encoder-multilingual-large",
+            "license": "Apache-2.0"
+        }
     ],
-    "sources": [{
-        "name": "Universal Sentence Encoder Multilingual - Large",
-        "url": "https://tfhub.dev/google/universal-sentence-encoder-multilingual-large",
-        "license": "Apache-2.0"
-    }],
     "vectors": {
         "width": 512,
         "vectors": 0,
@@ -30,7 +32,5 @@
         "universal_sentence_encoder": "universal_sentence_encoder",
         "sentencizer": "sentencizer"
     },
-    "labels": {
-
-    }
+    "labels": {}
 }

spacy_universal_sentence_encoder/meta/xx_use_md.json

@@ -1,21 +1,23 @@
 {
     "lang": "xx",
     "name": "use_md",
-    "version": "0.4.5",
+    "version": "0.4.6",
     "spacy_version": ">=3.0,<4.0",
     "description": "TensorFlow Hub wrapper for Universal Sentence Encoder",
     "author": "Martino Mensio",
     "email": "[email protected]",
     "url": "https://github.com/MartinoMensio/spacy-universal-sentence-encoder",
     "license": "MIT",
     "requirements": [
-        "spacy-universal-sentence-encoder[multi]>=0.4.5"
+        "spacy-universal-sentence-encoder[multi]>=0.4.6"
+    ],
+    "sources": [
+        {
+            "name": "Universal Sentence Encoder Multilingual",
+            "url": "https://tfhub.dev/google/universal-sentence-encoder-multilingual",
+            "license": "Apache-2.0"
+        }
     ],
-    "sources": [{
-        "name": "Universal Sentence Encoder Multilingual",
-        "url": "https://tfhub.dev/google/universal-sentence-encoder-multilingual",
-        "license": "Apache-2.0"
-    }],
     "vectors": {
         "width": 512,
         "vectors": 0,
@@ -30,7 +32,5 @@
         "universal_sentence_encoder": "universal_sentence_encoder",
         "sentencizer": "sentencizer"
     },
-    "labels": {
-
-    }
+    "labels": {}
 }