French asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized WhisperForCTC from jwkritchie

Description

Pretrained WhisperForCTC model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized is a French model originally trained by jwkritchie.

This model is only compatible with PySpark 3.4 and above

Download Copy S3 URI

How to use


audioAssembler = AudioAssembler() \
    .setInputCol("audio_content") \
    .setOutputCol("audio_assembler")
    
    
speechToText  = WhisperForCTC.pretrained("asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized","fr") \
            .setInputCols(["audio_assembler"]) \
            .setOutputCol("text")

pipeline = Pipeline().setStages([audioAssembler, speechToText])

pipelineModel = pipeline.fit(data)

pipelineDF = pipelineModel.transform(data)


val audioAssembler = new AudioAssembler() 
    .setInputCol("audio_content") 
    .setOutputCol("audio_assembler")
    
val speechToText  = WhisperForCTC.pretrained("asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized","fr") 
            .setInputCols(Array("audio_assembler")) 
            .setOutputCol("text")

val pipeline = new Pipeline().setStages(Array(audioAssembler, speechToText))

val pipelineModel = pipeline.fit(data)

val pipelineDF = pipelineModel.transform(data)


Model Information

Model Name: asr_whisper_small_defined_dot_ai_qc_french_combined_dataset_normalized
Compatibility: Spark NLP 5.1.4+
License: Open Source
Edition: Official
Input Labels: [audio_assembler]
Output Labels: [text]
Language: fr
Size: 1.7 GB

References

https://huggingface.co/jwkritchie/whisper-small-defined-dot-ai-qc-fr-combined-dataset-normalized