deepdml
/

whisper-large-v3-turbo

Automatic Speech Recognition

Safetensors

whisper

audio

hf-asr-leaderboard

Model card Files Files and versions Community

deepdml commited on about 13 hours ago

Commit

d4e5c2a

•

1 Parent(s): 5da21a7

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -148,7 +148,7 @@ from datasets import load_dataset
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-model_id = "ylacombe/whisper-large-v3-turbo"
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
@@ -252,7 +252,7 @@ from datasets import Audio, load_dataset
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-model_id = "ylacombe/whisper-large-v3-turbo"
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
@@ -327,7 +327,7 @@ from datasets import load_dataset
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-model_id = "ylacombe/whisper-large-v3-turbo"
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
@@ -373,7 +373,7 @@ torch.set_float32_matmul_precision("high")
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
-model_id = "ylacombe/whisper-large-v3-turbo"
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
@@ -472,7 +472,7 @@ checkpoints are summarised in the following table with links to the models on th
 | large    | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large)    |
 | large-v2 | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large-v2) |
 | large-v3 | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large-v3) |
-| large-v3-turbo | 809 M     | x                                                    | [✓](https://huggingface.co/ylacombe/whisper-large-v3-turbo) |
 ## Fine-Tuning

 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+model_id = "deepdml/whisper-large-v3-turbo"
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+model_id = "deepdml/whisper-large-v3-turbo"
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+model_id = "deepdml/whisper-large-v3-turbo"
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
 device = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+model_id = "deepdml/whisper-large-v3-turbo"
 model = AutoModelForSpeechSeq2Seq.from_pretrained(
     model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True
 | large    | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large)    |
 | large-v2 | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large-v2) |
 | large-v3 | 1550 M     | x                                                    | [✓](https://huggingface.co/openai/whisper-large-v3) |
+| large-v3-turbo | 809 M     | x                                                    | [✓](https://huggingface.co/deepdml/whisper-large-v3-turbo) |
 ## Fine-Tuning