cinemasetfree
ibm-granite/granite-speech-3.3-8b
Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
audio | array | Audio inputs for the model. | — | — |
chat_template | string | A template to format the prompt with. If not provided, the default prompt template will be used. | — | — |
frequency_penalty | number | Frequency penalty | 0 | — |
max_tokens | integer | The maximum number of tokens the model should generate as output. | 512 | — |
min_tokens | integer | The minimum number of tokens the model should generate as output. | 0 | — |
presence_penalty | number | Presence penalty | 0 | — |
prompt | string | User prompt to send to the model. | "" | — |
seed | integer | Random seed. Leave blank to randomize the seed. | — | — |
stop_sequences | string | A comma-separated list of sequences to stop generation at. For example, '<end>,<stop>' will stop generation at the first instance of 'end' or '<stop>'. | — | — |
system_prompt | string | System prompt to send to the model.The chat template provides a good default. | — | — |
temperature | number | The value used to modulate the next token probabilities. | 0.6 | — |
top_k | integer | The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering). | 50 | — |
top_p | number | A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751). | 0.9 | — |
audioarrayAudio inputs for the model.
chat_templatestringA template to format the prompt with. If not provided, the default prompt template will be used.
frequency_penaltynumberFrequency penalty
0max_tokensintegerThe maximum number of tokens the model should generate as output.
512min_tokensintegerThe minimum number of tokens the model should generate as output.
0presence_penaltynumberPresence penalty
0promptstringUser prompt to send to the model.
""seedintegerRandom seed. Leave blank to randomize the seed.
stop_sequencesstringA comma-separated list of sequences to stop generation at. For example, '<end>,<stop>' will stop generation at the first instance of 'end' or '<stop>'.
system_promptstringSystem prompt to send to the model.The chat template provides a good default.
temperaturenumberThe value used to modulate the next token probabilities.
0.6top_kintegerThe number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).
50top_pnumberA probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
0.9688e7a943167Updated: 8/1/202620.6K runs