JohnSnowLabs · maziyarpanahi · Aug 25, 2023 · Nov 21, 2022 · Nov 25, 2022 · Dec 15, 2022
diff --git a/docs/_posts/DevinTDHa/2023-08-22-asr_whisper_tiny_opt_xx.md b/docs/_posts/DevinTDHa/2023-08-22-asr_whisper_tiny_opt_xx.md
@@ -0,0 +1,109 @@
+---
+layout: model
+title: Official whisper-tiny Optimized
+author: John Snow Labs
+name: asr_whisper_tiny_opt
+date: 2023-08-22
+tags: [whisper, en, audio, open_source, asr, onnx, xx]
+task: Automatic Speech Recognition
+language: xx
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: onnx
+annotator: WhisperForCTC
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Official pretrained Whisper model, adapted from HuggingFace transformer and curated to provide scalability and production-readiness using Spark NLP.
+
+This is a multilingual model and supports the following languages:
+
+Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.
+
+## Predicted Entities
+
+
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/asr_whisper_tiny_opt_xx_5.1.0_3.0_1692721787993.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/asr_whisper_tiny_opt_xx_5.1.0_3.0_1692721787993.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+import sparknlp
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+audioAssembler = AudioAssembler() \
+    .setInputCol("audio_content") \
+    .setOutputCol("audio_assembler")
+
+speechToText = WhisperForCTC.pretrained("asr_whisper_tiny_opt", "xx") \
+    .setInputCols(["audio_assembler"]) \
+    .setOutputCol("text")
+
+pipeline = Pipeline().setStages([audioAssembler, speechToText])
+processedAudioFloats = spark.createDataFrame([[rawFloats]]).toDF("audio_content")
+result = pipeline.fit(processedAudioFloats).transform(processedAudioFloats)
+result.select("text.result").show(truncate = False)
+```
+```scala
+import spark.implicits._
+import com.johnsnowlabs.nlp.base._
+import com.johnsnowlabs.nlp.annotators._
+import com.johnsnowlabs.nlp.annotators.audio.WhisperForCTC
+import org.apache.spark.ml.Pipeline
+
+val audioAssembler: AudioAssembler = new AudioAssembler()
+  .setInputCol("audio_content")
+  .setOutputCol("audio_assembler")
+
+val speechToText: WhisperForCTC = WhisperForCTC
+  .pretrained("asr_whisper_tiny_opt", "xx") 
+  .setInputCols("audio_assembler")
+  .setOutputCol("text")
+
+val pipeline: Pipeline = new Pipeline().setStages(Array(audioAssembler, speechToText))
+
+val bufferedSource =
+  scala.io.Source.fromFile("src/test/resources/audio/txt/librispeech_asr_0.txt")
+
+val rawFloats = bufferedSource
+  .getLines()
+  .map(_.split(",").head.trim.toFloat)
+  .toArray
+bufferedSource.close
+
+val processedAudioFloats = Seq(rawFloats).toDF("audio_content")
+
+val result = pipeline.fit(processedAudioFloats).transform(processedAudioFloats)
+result.select("text.result").show(truncate = false)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|asr_whisper_tiny_opt|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[audio_assembler]|
+|Output Labels:|[text]|
+|Language:|xx|
+|Size:|242.7 MB|
diff --git a/docs/_posts/DevinTDHa/2023-08-22-asr_whisper_tiny_xx.md b/docs/_posts/DevinTDHa/2023-08-22-asr_whisper_tiny_xx.md
@@ -0,0 +1,109 @@
+---
+layout: model
+title: Official whisper-tiny
+author: John Snow Labs
+name: asr_whisper_tiny
+date: 2023-08-22
+tags: [whisper, en, audio, open_source, asr, xx, tensorflow]
+task: Automatic Speech Recognition
+language: xx
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: WhisperForCTC
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Official pretrained Whisper model, adapted from HuggingFace transformer and curated to provide scalability and production-readiness using Spark NLP.
+
+This is a multilingual model and supports the following languages:
+
+Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.
+
+## Predicted Entities
+
+
+
+{:.btn-box}
+<button class="button button-orange" disabled>Live Demo</button>
+<button class="button button-orange" disabled>Open in Colab</button>
+[Download](https://s3.amazonaws.com/auxdata.johnsnowlabs.com/public/models/asr_whisper_tiny_xx_5.1.0_3.0_1692723111563.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/asr_whisper_tiny_xx_5.1.0_3.0_1692723111563.zip){:.button.button-orange.button-orange-trans.button-icon.button-copy-s3}
+
+## How to use
+
+
+
+<div class="tabs-box" markdown="1">
+{% include programmingLanguageSelectScalaPythonNLU.html %}
+```python
+import sparknlp
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+audioAssembler = AudioAssembler() \
+    .setInputCol("audio_content") \
+    .setOutputCol("audio_assembler")
+
+speechToText = WhisperForCTC.pretrained("asr_whisper_tiny", "xx") \
+    .setInputCols(["audio_assembler"]) \
+    .setOutputCol("text")
+
+pipeline = Pipeline().setStages([audioAssembler, speechToText])
+processedAudioFloats = spark.createDataFrame([[rawFloats]]).toDF("audio_content")
+result = pipeline.fit(processedAudioFloats).transform(processedAudioFloats)
+result.select("text.result").show(truncate = False)
+```
+```scala
+import spark.implicits._
+import com.johnsnowlabs.nlp.base._
+import com.johnsnowlabs.nlp.annotators._
+import com.johnsnowlabs.nlp.annotators.audio.WhisperForCTC
+import org.apache.spark.ml.Pipeline
+
+val audioAssembler: AudioAssembler = new AudioAssembler()
+  .setInputCol("audio_content")
+  .setOutputCol("audio_assembler")
+
+val speechToText: WhisperForCTC = WhisperForCTC
+  .pretrained("asr_whisper_tiny", "xx") 
+  .setInputCols("audio_assembler")
+  .setOutputCol("text")
+
+val pipeline: Pipeline = new Pipeline().setStages(Array(audioAssembler, speechToText))
+
+val bufferedSource =
+  scala.io.Source.fromFile("src/test/resources/audio/txt/librispeech_asr_0.txt")
+
+val rawFloats = bufferedSource
+  .getLines()
+  .map(_.split(",").head.trim.toFloat)
+  .toArray
+bufferedSource.close
+
+val processedAudioFloats = Seq(rawFloats).toDF("audio_content")
+
+val result = pipeline.fit(processedAudioFloats).transform(processedAudioFloats)
+result.select("text.result").show(truncate = false)
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|asr_whisper_tiny|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[audio_assembler]|
+|Output Labels:|[text]|
+|Language:|xx|
+|Size:|156.6 MB|
diff --git a/docs/_posts/ahmedlone127/2023-05-19-match_pattern_en.md b/docs/_posts/ahmedlone127/2023-05-19-match_pattern_en.md
@@ -33,16 +33,7 @@ The match_pattern is a pretrained pipeline that we can use to process text with
 
 ## How to use
 
-<div class="tabs-box" markdown="1">
-{% include programmingLanguageSelectScalaPythonNLU.html %}
-```python
 
-from sparknlp.pretrained import PretrainedPipeline
-pipeline = PretrainedPipeline("match_pattern", "en", "clinical/models")
-	result = pipeline.annotate("""I love johnsnowlabs!  """)
-```
-
-</div>
 
 {:.model-param}
 

diff --git a/docs/_posts/ahmedlone127/2023-05-20-analyze_sentiment_en.md b/docs/_posts/ahmedlone127/2023-05-20-analyze_sentiment_en.md
@@ -34,39 +34,7 @@ It performs most of the common text processing tasks on your dataframe
 
 ## How to use
 
-<div class="tabs-box" markdown="1">
-{% include programmingLanguageSelectScalaPythonNLU.html %}
-
-```python
-
-from sparknlp.pretrained import PretrainedPipeline
-
-pipeline = PretrainedPipeline('analyze_sentiment', lang = 'en')
-
-result = pipeline.fullAnnotate("""Demonicus is a movie turned into a video game! I just love the story and the things that goes on in the film.It is a B-film ofcourse but that doesn`t bother one bit because its made just right and the music was rad! Horror and sword fight freaks,buy this movie now!""")
-
-
-```
-```scala
-
-import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
 
-val pipeline = new PretrainedPipeline("analyze_sentiment", lang = "en")
-
-val result = pipeline.fullAnnotate("""Demonicus is a movie turned into a video game! I just love the story and the things that goes on in the film.It is a B-film ofcourse but that doesn`t bother one bit because its made just right and the music was rad! Horror and sword fight freaks,buy this movie now!""")
-
-```
-
-{:.nlu-block}
-```python
-
-import nlu
-text = ["""Demonicus is a movie turned into a video game! I just love the story and the things that goes on in the film.It is a B-film ofcourse but that doesn`t bother one bit because its made just right and the music was rad! Horror and sword fight freaks,buy this movie now!"""]
-result_df = nlu.load('en.classify').predict(text)
-result_df
-
-```
-</div>
 
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}

diff --git a/docs/_posts/ahmedlone127/2023-05-20-clean_pattern_en.md b/docs/_posts/ahmedlone127/2023-05-20-clean_pattern_en.md
@@ -34,33 +34,7 @@ The clean_pattern is a pretrained pipeline that we can use to process text with
 
 ## How to use
 
-<div class="tabs-box" markdown="1">
-{% include programmingLanguageSelectScalaPythonNLU.html %}
-```python
-
-
-from sparknlp.pretrained import PretrainedPipelinein
-pipeline = PretrainedPipeline('clean_pattern', lang = 'en')
-annotations =  pipeline.fullAnnotate(""Hello from John Snow Labs ! "")[0]
-annotations.keys()
-```
-```scala
-
-
-val pipeline = new PretrainedPipeline("clean_pattern", lang = "en")
-val result = pipeline.fullAnnotate("Hello from John Snow Labs ! ")(0)
-```
-
-{:.nlu-block}
-```python
-
 
-import nlu
-text = [""Hello from John Snow Labs ! ""]
-result_df = nlu.load('en.clean.pattern').predict(text)
-result_df
-```
-</div>
 
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}

diff --git a/docs/_posts/ahmedlone127/2023-05-20-clean_stop_en.md b/docs/_posts/ahmedlone127/2023-05-20-clean_stop_en.md
@@ -34,35 +34,8 @@ It performs most of the common text processing tasks on your dataframe
 
 ## How to use
 
-<div class="tabs-box" markdown="1">
-{% include programmingLanguageSelectScalaPythonNLU.html %}
-```python
-
-from sparknlp.pretrained import PretrainedPipelinein
-pipeline = PretrainedPipeline('clean_stop', lang = 'en')
-annotations =  pipeline.fullAnnotate(""Hello from John Snow Labs ! "")[0]
-annotations.keys()
-
-```
-```scala
-
-val pipeline = new PretrainedPipeline("clean_stop", lang = "en")
-val result = pipeline.fullAnnotate("Hello from John Snow Labs ! ")(0)
 
 
-```
-
-{:.nlu-block}
-```python
-
-import nlu
-text = [""Hello from John Snow Labs ! ""]
-result_df = nlu.load('en.clean.stop').predict(text)
-result_df
-
-```
-</div>
-
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}
 ```python

diff --git a/docs/_posts/ahmedlone127/2023-05-20-entity_recognizer_lg_fr.md b/docs/_posts/ahmedlone127/2023-05-20-entity_recognizer_lg_fr.md
@@ -34,35 +34,8 @@ It performs most of the common text processing tasks on your dataframe
 
 ## How to use
 
-<div class="tabs-box" markdown="1">
-{% include programmingLanguageSelectScalaPythonNLU.html %}
-```python
-
-from sparknlp.pretrained import PretrainedPipelinein
-pipeline = PretrainedPipeline('entity_recognizer_lg', lang = 'fr')
-annotations =  pipeline.fullAnnotate(""Bonjour de John Snow Labs! "")[0]
-annotations.keys()
-
-```
-```scala
-
-val pipeline = new PretrainedPipeline("entity_recognizer_lg", lang = "fr")
-val result = pipeline.fullAnnotate("Bonjour de John Snow Labs! ")(0)
 
 
-```
-
-{:.nlu-block}
-```python
-
-import nlu
-text = [""Bonjour de John Snow Labs! ""]
-result_df = nlu.load('fr.ner').predict(text)
-result_df
-
-```
-</div>
-
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}
 ```python