bofenghuang
/

whisper-large-v2-cv11-german

Automatic Speech Recognition

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

bofenghuang commited on Dec 27, 2022

Commit

cee265c

•

1 Parent(s): 124879f

up

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -56,9 +56,9 @@ This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingf
 | Model | Common Voice 11.0 |
 | --- | :---: |
-| [bofenghuang/whisper-small-cv11-german-punct](https://huggingface.co/bofenghuang/whisper-small-cv11-german-punct) | 11.35 |
-| [bofenghuang/whisper-medium-cv11-german-punct](https://huggingface.co/bofenghuang/whisper-medium-cv11-german-punct) | 7.05 |
-| [bofenghuang/whisper-large-v2-cv11-german-punct](https://huggingface.co/bofenghuang/whisper-large-v2-cv11-german-punct) | **5.76** |
 ## Usage
@@ -73,7 +73,7 @@ from transformers import pipeline
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 # Load pipeline
-pipe = pipeline("automatic-speech-recognition", model="bofenghuang/whisper-large-v2-cv11-german-punct", device=device)
 # NB: set forced_decoder_ids for generation utils
 pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="de", task="transcribe")
@@ -111,8 +111,8 @@ from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 # Load model
-model = AutoModelForSpeechSeq2Seq.from_pretrained("bofenghuang/whisper-large-v2-cv11-german-punct").to(device)
-processor = AutoProcessor.from_pretrained("bofenghuang/whisper-large-v2-cv11-german-punct", language="german", task="transcribe")
 # NB: set forced_decoder_ids for generation utils
 model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="de", task="transcribe")

 | Model | Common Voice 11.0 |
 | --- | :---: |
+| [bofenghuang/whisper-small-cv11-german](https://huggingface.co/bofenghuang/whisper-small-cv11-german) | 11.35 |
+| [bofenghuang/whisper-medium-cv11-german](https://huggingface.co/bofenghuang/whisper-medium-cv11-german) | 7.05 |
+| [bofenghuang/whisper-large-v2-cv11-german](https://huggingface.co/bofenghuang/whisper-large-v2-cv11-german) | **5.76** |
 ## Usage
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 # Load pipeline
+pipe = pipeline("automatic-speech-recognition", model="bofenghuang/whisper-large-v2-cv11-german", device=device)
 # NB: set forced_decoder_ids for generation utils
 pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="de", task="transcribe")
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 # Load model
+model = AutoModelForSpeechSeq2Seq.from_pretrained("bofenghuang/whisper-large-v2-cv11-german").to(device)
+processor = AutoProcessor.from_pretrained("bofenghuang/whisper-large-v2-cv11-german", language="german", task="transcribe")
 # NB: set forced_decoder_ids for generation utils
 model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(language="de", task="transcribe")