openai/whisper-large-v3-turbo
openai/whisper-large-v3-turbo
2
1
Overview Code Discussions Pull Requests Wiki Activity

Update README.md (#4)

Browse Source 
- Update README.md (c329f74454be12bf7e475f5406b456f7a5855f96)


Co-authored-by: Vaibhav Srivastav <reach-vb@users.noreply.huggingface.co>
This commit is contained in:
Yoach Lacombe 2024-10-02 08:21:21 +00:00 committed by system
parent 45f16f295c
commit bb8db30333
No known key found for this signature in database
GPG Key ID: 6A528E38E0733467
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -119,8 +119,8 @@ Whisper is a state-of-the-art model for automatic speech recognition (ASR) and s
et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many
datasets and domains in a zero-shot setting.
Whisper large-v3-turbo is a distilled version of [Whisper large-v3](https://huggingface.co/openai/whisper-large-v3). In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4.
As a result, the model is way faster, at the expense of a minor quality degradation.
Whisper large-v3-turbo is a finetuned version of a pruned [Whisper large-v3](https://huggingface.co/openai/whisper-large-v3). In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4.
As a result, the model is way faster, at the expense of a minor quality degradation. You can find more details about it [in this GitHub discussion](https://github.com/openai/whisper/discussions/2363).
**Disclaimer**: Content for this model card has partly been written by the 🤗 Hugging Face team, and partly copied and
pasted from the original model card.
@ -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_id = "openai/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_id = "openai/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_id = "openai/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_id = "openai/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) |
| large-v3-turbo | 809 M | x | [✓](https://huggingface.co/openai/whisper-large-v3-turbo) |
## Fine-Tuning