KBLab/kb-whisper-large

`KBLab/kb-whisper-large` powered by Hugging Face Inference API - [Original Model Card](https://huggingface.co/KBLab/kb-whisper-large) - [`automatic-speech-recognition` Task on Hugging Face](https://h…

azureFoundry/HuggingFace/kblab-kb-whisper-large@1

KBLab/kb-whisper-large powered by Hugging Face Inference API

Send Request

You can use cURL or any REST Client to send a request to the Azure ML endpoint with your Azure ML token.

curl <AZUREML_ENDPOINT_URL> \
    -X POST \
    -H "Authorization: Bearer <AZUREML_TOKEN>" \
    -H "Content-Type: application/json" \
    -d '{"inputs":"https://github.com/ggml-org/whisper.cpp/raw/b0a11594aec50892a02cd8d129eee2dfe93a8bb8/samples/jfk.wav","parameters":{"return_timestamps":true,"generation_parameters":{"task":"transcribe","language":"en"}}}'

Supported Parameters

  • inputs (string): The input audio data as a URL, a file or a base64-encoded string.
  • parameters (object):
    • return_timestamps (boolean): Whether to output corresponding timestamps with the generated text.
    • generation_parameters (object):
      • temperature (float): The value used to modulate the next token probabilities.
      • top_k (integer): The number of highest probability vocabulary tokens to keep for top-k-filtering.
      • top_p (float): If set to float < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.
      • typical_p (float): Local typicality measures how similar the conditional probability of predicting a target token next is to the expected conditional probability of predicting a random token next, given the partial text already generated. If set to float < 1, the smallest set of the most locally typical tokens with probabilities that add up to typical_p or higher are kept for generation. See this paper for more details.
      • epsilon_cutoff (float): If set to float strictly between 0 and 1, only tokens with a conditional probability greater than epsilon_cutoff will be sampled. In the paper, suggested values range from 3e-4 to 9e-4, depending on the size of the model. See Truncation Sampling as Language Model Desmoothing for more details.
      • eta_cutoff (float): Eta sampling is a hybrid of locally typical sampling and epsilon sampling. If set to float strictly between 0 and 1, a token is only considered if it is greater than either eta_cutoff or sqrt(eta_cutoff) * exp(-entropy(softmax(next_token_logits))). The latter term is intuitively the expected next token probability, scaled by sqrt(eta_cutoff). In the paper, suggested values range from 3e-4 to 2e-3, depending on the size of the model. See Truncation Sampling as Language Model Desmoothing for more details.
      • max_length (integer): The maximum length (in tokens) of the generated text, including the input.
      • max_new_tokens (integer): The maximum number of tokens to generate. Takes precedence over max_length.
      • min_length (integer): The minimum length (in tokens) of the generated text, including the input.
      • min_new_tokens (integer): The minimum number of tokens to generate. Takes precedence over min_length.
      • do_sample (boolean): Whether to use sampling instead of greedy decoding when generating new tokens.
      • early_stopping (enum): Possible values: never, true, false.
      • num_beams (integer): Number of beams to use for beam search.
      • num_beam_groups (integer): Number of groups to divide num_beams into in order to ensure diversity among different groups of beams. See this paper for more details.
      • penalty_alpha (float): The value balances the model confidence and the degeneration penalty in contrastive search decoding.
      • use_cache (boolean): Whether the model should use the past last key/values attentions to speed up decoding.

Note generation_parameters defined above are the "officially" supported ones, but anything that's provided inside generation_parameters will be forwarded to the underlying model via generation_kwargs as some models might support parameters that are not defined in the above listing.

Check the full API Specification at the Hugging Face Inference API Documentation.

Specifications & capabilities

Input
audio
Output
text
Published model ID
kb-whisper-large
Capabilities
audioInput

Provider specifications & access

1–1 / 1

KBLab/kb-whisper-large ↗

source model id
HuggingFace/kblab-kb-whisper-large@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • audio
output_modalities
  • text
capabilities

    Original sources

    1–4 / 4

    Hugging Face · KBLab/kb-whisper-large ↗

    Microsoft Foundry · Model page ↗

    Microsoft Foundry · Model documentation ↗

    Microsoft Foundry · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace