JohnSnowLabs
diff --git a/‎docs/_posts/DevinTDHa/2023-08-22-asr_whisper_tiny_opt_xx.md‎
Lines changed: 109 additions & 0 deletions b/‎docs/_posts/DevinTDHa/2023-08-22-asr_whisper_tiny_opt_xx.md‎
Lines changed: 109 additions & 0 deletions
diff --git a/‎docs/_posts/DevinTDHa/2023-08-22-asr_whisper_tiny_xx.md‎
Lines changed: 109 additions & 0 deletions b/‎docs/_posts/DevinTDHa/2023-08-22-asr_whisper_tiny_xx.md‎
Lines changed: 109 additions & 0 deletions
diff --git a/‎docs/_posts/ahmedlone127/2023-08-18-mpnet_embedding_579_STmodel_product_rem_v3a_en.md‎
Lines changed: 88 additions & 0 deletions b/‎docs/_posts/ahmedlone127/2023-08-18-mpnet_embedding_579_STmodel_product_rem_v3a_en.md‎
Lines changed: 88 additions & 0 deletions
diff --git a/‎docs/_posts/ahmedlone127/2023-08-18-mpnet_embedding_ATTACK_BERT_en.md‎
Lines changed: 88 additions & 0 deletions b/‎docs/_posts/ahmedlone127/2023-08-18-mpnet_embedding_ATTACK_BERT_en.md‎
Lines changed: 88 additions & 0 deletions
@@ -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|
@@ -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|
@@ -0,0 +1,88 @@
+---
+layout: model
+title: English mpnet_embedding_579_STmodel_product_rem_v3a TFMPNetModel from jamiehudson
+author: John Snow Labs
+name: mpnet_embedding_579_STmodel_product_rem_v3a
+date: 2023-08-18
+tags: [mpnet, en, open_source, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: MPNetEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained mpnet  model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mpnet_embedding_579_STmodel_product_rem_v3a` is a English model originally trained by jamiehudson.
+
+{:.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/mpnet_embedding_579_STmodel_product_rem_v3a_en_5.1.0_3.0_1692379340262.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mpnet_embedding_579_STmodel_product_rem_v3a_en_5.1.0_3.0_1692379340262.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
+
+document_assembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("documents")
+
+instruction = MPNetEmbeddings \
+    .pretrained("mpnet_embedding_579_STmodel_product_rem_v3a", "en")\
+    .setInputCols(["documents"]) \
+    .setOutputCol("mpnet_embeddings")
+
+pipeline = Pipeline(stages=[
+  document_assembler,
+  instruction,
+])
+
+pipelineModel = pipeline.fit(data)
+
+pipelineDF = pipelineModel.transform(data)
+```
+```scala
+
+val document_assembler = new DocumentAssembler()
+    .setInputCol("text") 
+    .setOutputCol("documents")
+
+val instruction = MPNetEmbeddings
+    .pretrained("mpnet_embedding_579_STmodel_product_rem_v3a", "en")
+    .setInputCols(Array("documents")) 
+    .setOutputCol("mpnet_embeddings") 
+
+val pipeline = new Pipeline().setStages(Array(document_assembler, instruction))
+
+val pipelineModel = pipeline.fit(data)
+
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|mpnet_embedding_579_STmodel_product_rem_v3a|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[mpnet_embeddings]|
+|Language:|en|
+|Size:|410.2 MB|
@@ -0,0 +1,88 @@
+---
+layout: model
+title: English mpnet_embedding_ATTACK_BERT TFMPNetModel from basel
+author: John Snow Labs
+name: mpnet_embedding_ATTACK_BERT
+date: 2023-08-18
+tags: [mpnet, en, open_source, tensorflow]
+task: Embeddings
+language: en
+edition: Spark NLP 5.1.0
+spark_version: 3.0
+supported: true
+engine: tensorflow
+annotator: MPNetEmbeddings
+article_header:
+  type: cover
+use_language_switcher: "Python-Scala-Java"
+---
+
+## Description
+
+Pretrained mpnet  model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.`mpnet_embedding_ATTACK_BERT` is a English model originally trained by basel.
+
+{:.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/mpnet_embedding_ATTACK_BERT_en_5.1.0_3.0_1692376584683.zip){:.button.button-orange.button-orange-trans.arr.button-icon}
+[Copy S3 URI](s3://auxdata.johnsnowlabs.com/public/models/mpnet_embedding_ATTACK_BERT_en_5.1.0_3.0_1692376584683.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
+
+document_assembler = DocumentAssembler() \
+    .setInputCol("text") \
+    .setOutputCol("documents")
+
+instruction = MPNetEmbeddings \
+    .pretrained("mpnet_embedding_ATTACK_BERT", "en")\
+    .setInputCols(["documents"]) \
+    .setOutputCol("mpnet_embeddings")
+
+pipeline = Pipeline(stages=[
+  document_assembler,
+  instruction,
+])
+
+pipelineModel = pipeline.fit(data)
+
+pipelineDF = pipelineModel.transform(data)
+```
+```scala
+
+val document_assembler = new DocumentAssembler()
+    .setInputCol("text") 
+    .setOutputCol("documents")
+
+val instruction = MPNetEmbeddings
+    .pretrained("mpnet_embedding_ATTACK_BERT", "en")
+    .setInputCols(Array("documents")) 
+    .setOutputCol("mpnet_embeddings") 
+
+val pipeline = new Pipeline().setStages(Array(document_assembler, instruction))
+
+val pipelineModel = pipeline.fit(data)
+
+val pipelineDF = pipelineModel.transform(data)
+
+```
+</div>
+
+{:.model-param}
+## Model Information
+
+{:.table-model}
+|---|---|
+|Model Name:|mpnet_embedding_ATTACK_BERT|
+|Compatibility:|Spark NLP 5.1.0+|
+|License:|Open Source|
+|Edition:|Official|
+|Input Labels:|[documents]|
+|Output Labels:|[mpnet_embeddings]|
+|Language:|en|
+|Size:|409.8 MB|