@misc{hf_model__okestro_ai_lab__symphony_asr,
author = {Okestro Ai Lab},
title = {Symphony Asr Model},
year = {2026},
howpublished = {\url{https://huggingface.co/okestro-ai-lab/symphony-asr}},
note = {Accessed via Free2AITools Knowledge Fortress}
}
APA Style
Okestro Ai Lab. (2026). Symphony Asr [Model]. Free2AITools. https://huggingface.co/okestro-ai-lab/symphony-asr
You can easily load the model using AutoModelForCausalLM.from_pretrained. This model includes custom code, so the trust_remote_code=True option is required.
python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
# âŦ ī¸ Enter your Hugging Face repository ID here.
repo_id = "okestro-ai-lab/SYMPHONY-ASR"
model = AutoModelForCausalLM.from_pretrained(
repo_id,
trust_remote_code=True,
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(repo_id)
generation_config = GenerationConfig.from_pretrained(repo_id)
model.eval()
This example shows how to load an audio file and transcribe it to text.
python
import torch
import librosa
# 1. Load and resample the audio file
# âŦ ī¸ Path to the audio file to be transcribed
wav_path = "sample_audio/English_audio.wav"
wav,sample_rate = librosa.load(wav_path)
# SYMPHONY-ASR requires 16kHz audio.
if sample_rate != 16000:
audio = librosa.resample(wav,orig_sr=sample_rate,target_sr=16000)
else:
audio = wav
# 2. Prepare the prompt and tokenize the prompt
# Automatic Speech Recognition (ASR) task
# Addiational Tasks: please refer to Supported Tasks
# A task token is not required, but it is recommended for achieving a more appropriate task.
TASK_TOKEN = "<|ASR|>"
AUDIO_TOKEN = "<|audio_bos|><|AUDIO|><|audio_eos|>"
user_prompt = f"{TASK_TOKEN}{AUDIO_TOKEN}\nTranscribe the audio clip into text."
prompt = [{"role": "user", "content": user_prompt}]
input_ids = tokenizer.apply_chat_template(
prompt,
add_generation_prompt=True,
tokenize=True,
return_tensors='pt'
).to(model.device)
# 3. Perform inference
# The model's generate function expects the audio input as a list.
audio_tensor = torch.tensor((audio,),dtype=torch.float32).cuda()
with torch.no_grad():
with torch.cuda.amp.autocast(dtype=torch.bfloat16):
output_ids = model.generate(
input_ids=input_ids,
audio=audio_tensor,
generation_config=generation_config,
max_new_tokens=256
)
# 5. Decode the result
transcription = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0]
print("--- Transcription Result ---")
print(transcription)
đ Supported Tasks
You can perform different tasks by using the following special tokens in your prompt:
<|ASR|>: Automatic Speech Recognition - Transcribes audio into text.
<|AST|>: Automatic Speech Translation - Translates audio into text of another language.
<|SSUM|>: Speech Summarization - Summarizes the content of an audio clip.
<|SQQA|>: Spoken Query-based Question Answering - Answers questions based on the content of an audio clip.
⥠GPU Requirements
SYMPHONY-ASR inference requires a GPU with sufficient memory.
Task
Recommended GPU
Minimum VRAM
Inference
NVIDIA A100 / H100
âĨ 11.8 GB
đĄ Using mixed precision (bfloat16 or fp16) is recommended to reduce memory usage.
â ī¸ Incomplete Data
Some information about this model is not available.
Use with Caution - Verify details from the original source before relying on this data.